Xiaohan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Xiaohan Wang has a total of 71 co-authors. Here are the top co-authors by number of shared publications:
- Yi Yang
Zhejiang University, China
24 shared publications - Linchao Zhu
College of Computer Science and Technology Zhejiang University
13 shared publications - Zhedong Zheng
University of Macau, Macau, China
4 shared publications - Wenguan Wang
Zhejiang University
3 shared publications - Fei Wu
Zhejiang University
2 shared publications - James Ainooson
Vanderbilt University 37240 Nashville TN USA
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6069-6078
GLANCE: A Global–Local Coordination Multi-Agent Framework for Music-Grounded Non-Linear Video Editing
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6069-6078
Open AccessGLANCE: A Global–Local Coordination Multi-Agent Framework for Music-Grounded Non-Linear Video Editing
- 26 September 2024
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (3) , 1222-1237
Slimmable Networks for Contrastive Self-supervised Learning
- 26 September 2024
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (3) , 1222-1237
Slimmable Networks for Contrastive Self-supervised Learning
- 9 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (7) , 5223-5237
Cap4Video++: Enhancing Video Understanding With Auxiliary Captions
Understanding videos, especially aligning them with textual data, presents a significant challenge in computer vision. The advent of vision-language models (VLMs) like CLIP has sparked interest in leveraging their capabilities for enhanced video understanding, showing marked advancements in both performance and efficiency. However, current methods often neglect vital user-generated metadata such as video titles. In this paper, we present Cap4Video++, a universal framework that leverages auxiliary captions to enrich video understanding. More recently, we witness the flourishing of large language models (LLMs) like ChatGPT. Cap4Video++ harnesses the synergy of vision-language models (VLMs) and large language models (LLMs) to generate video captions, utilized in three key phases: (i) Input stage employs Semantic Pair Sampling to extract beneficial samples from captions, aiding contrastive learning. (ii) Intermediate stage sees Video-Caption Cross-modal Interaction and Adaptive Caption Selection work together to bolster video and caption representations. (iii) Output stage introduces a Complementary Caption-Text Matching branch, enhancing the primary video branch by improving similarity calculations. Our comprehensive experiments on text-video retrieval and video action recognition across nine benchmarks clearly demonstrate Cap4Video++'s superiority over existing models, highlighting its effectiveness in utilizing automatically generated captions to advance video understanding.
- 9 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (7) , 5223-5237
Cap4Video++: Enhancing Video Understanding With Auxiliary Captions
Understanding videos, especially aligning them with textual data, presents a significant challenge in computer vision. The advent of vision-language models (VLMs) like CLIP has sparked interest in leveraging their capabilities for enhanced video understanding, showing marked advancements in both performance and efficiency. However, current methods often neglect vital user-generated metadata such as video titles. In this paper, we present Cap4Video++, a universal framework that leverages auxiliary captions to enrich video understanding. More recently, we witness the flourishing of large language models (LLMs) like ChatGPT. Cap4Video++ harnesses the synergy of vision-language models (VLMs) and large language models (LLMs) to generate video captions, utilized in three key phases: (i) Input stage employs Semantic Pair Sampling to extract beneficial samples from captions, aiding contrastive learning. (ii) Intermediate stage sees Video-Caption Cross-modal Interaction and Adaptive Caption Selection work together to bolster video and caption representations. (iii) Output stage introduces a Complementary Caption-Text Matching branch, enhancing the primary video branch by improving similarity calculations. Our comprehensive experiments on text-video retrieval and video action recognition across nine benchmarks clearly demonstrate Cap4Video++'s superiority over existing models, highlighting its effectiveness in utilizing automatically generated captions to advance video understanding.
- 2 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (9) , 6247-6262
Scalable Video Object Segmentation With Identification Mechanism
This paper delves into the challenges of achieving scalable and effective multi-object modeling for semi-supervised Video Object Segmentation (VOS). Previous VOS methods decode features with a single positive object, limiting the learning of multi-object representation as they must match and segment each target separately under multi-object scenarios. Additionally, earlier techniques catered to specific application objectives and lacked the flexibility to fulfill different speed-accuracy requirements. To address these problems, we present two innovative approaches, Associating Objects with Transformers (AOT) and Associating Objects with Scalable Transformers (AOST). In pursuing effective multi-object modeling, AOT introduces the IDentification (ID) mechanism to allocate each object a unique identity. This approach enables the network to model the associations among all objects simultaneously, thus facilitating the tracking and segmentation of objects in a single network pass. To address the challenge of inflexible deployment, AOST further integrates scalable long short-term transformers that incorporate scalable supervision and layer-wise ID-based attention. This enables online architecture scalability in VOS for the first time and overcomes ID embeddings' representation limitations. Given the absence of a benchmark for VOS involving densely multi-object annotations, we propose a challenging Video Object Segmentation in the Wild (VOSW) benchmark to validate our approaches. We evaluated various AOT and AOST variants using extensive experiments across VOSW and five commonly used VOS benchmarks, including YouTube-VOS 2018 & 2019 Val, DAVIS-2017 Val & Test, and DAVIS-2016. Our approaches surpass the state-of-the-art competitors and display exceptional efficiency and scalability consistently across all six benchmarks. Moreover, we notably achieved the $\mathbf {1^{st}}$ position in the 3 rd Large-scale Video Object Segmentation Challenge. Project page: https://github.com/yoxu515/aot-benchmark .
- 2 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (9) , 6247-6262
Scalable Video Object Segmentation With Identification Mechanism
This paper delves into the challenges of achieving scalable and effective multi-object modeling for semi-supervised Video Object Segmentation (VOS). Previous VOS methods decode features with a single positive object, limiting the learning of multi-object representation as they must match and segment each target separately under multi-object scenarios. Additionally, earlier techniques catered to specific application objectives and lacked the flexibility to fulfill different speed-accuracy requirements. To address these problems, we present two innovative approaches, Associating Objects with Transformers (AOT) and Associating Objects with Scalable Transformers (AOST). In pursuing effective multi-object modeling, AOT introduces the IDentification (ID) mechanism to allocate each object a unique identity. This approach enables the network to model the associations among all objects simultaneously, thus facilitating the tracking and segmentation of objects in a single network pass. To address the challenge of inflexible deployment, AOST further integrates scalable long short-term transformers that incorporate scalable supervision and layer-wise ID-based attention. This enables online architecture scalability in VOS for the first time and overcomes ID embeddings' representation limitations. Given the absence of a benchmark for VOS involving densely multi-object annotations, we propose a challenging Video Object Segmentation in the Wild (VOSW) benchmark to validate our approaches. We evaluated various AOT and AOST variants using extensive experiments across VOSW and five commonly used VOS benchmarks, including YouTube-VOS 2018 & 2019 Val, DAVIS-2017 Val & Test, and DAVIS-2016. Our approaches surpass the state-of-the-art competitors and display exceptional efficiency and scalability consistently across all six benchmarks. Moreover, we notably achieved the $\mathbf {1^{st}}$ position in the 3 rd Large-scale Video Object Segmentation Challenge. Project page: https://github.com/yoxu515/aot-benchmark .
- Top Cited PapersOpen Access
- 26 March 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (6) , 1-18
Jointly Harnessing Prior Structures and Temporal Consistency for Sign Language Video Generation
Sign language provides a way for differently-abled individuals to express their feelings and emotions. However, learning sign language can be challenging and time consuming. An alternative approach is to animate user photos using sign language videos of specific words, which can be achieved using existing image animation methods. However, the finger motions in the generated videos are often not ideal. To address this issue, we propose the Structure-aware Temporal Consistency Network (STCNet), which jointly optimizes the prior structure of humans with temporal consistency to produce sign language videos. We use a fine-grained skeleton detector to acquire knowledge of body structure and introduce both short- and long-term cycle loss to ensure the continuity of the generated video. The two losses and keypoint detector network are optimized in an end-to-end manner. Quantitative and qualitative evaluations on three widely used datasets, namely LSA64, Phoenix-2014T, and WLASL-2000, demonstrate the effectiveness of the proposed method. It is our hope that this work can contribute to future studies on sign language production.
- 26 March 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (6) , 1-18
Top Cited PapersOpen AccessJointly Harnessing Prior Structures and Temporal Consistency for Sign Language Video Generation
Sign language provides a way for differently-abled individuals to express their feelings and emotions. However, learning sign language can be challenging and time consuming. An alternative approach is to animate user photos using sign language videos of specific words, which can be achieved using existing image animation methods. However, the finger motions in the generated videos are often not ideal. To address this issue, we propose the Structure-aware Temporal Consistency Network (STCNet), which jointly optimizes the prior structure of humans with temporal consistency to produce sign language videos. We use a fine-grained skeleton detector to acquire knowledge of body structure and introduce both short- and long-term cycle loss to ensure the continuity of the generated video. The two losses and keypoint detector network are optimized in an end-to-end manner. Quantitative and qualitative evaluations on three widely used datasets, namely LSA64, Phoenix-2014T, and WLASL-2000, demonstrate the effectiveness of the proposed method. It is our hope that this work can contribute to future studies on sign language production.
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (7) , 6540-6548
DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval
Text-video retrieval is a critical multi-modal task to find the most relevant video for a text query. Although pretrained models like CLIP have demonstrated impressive potential in this area, the rising cost of fully finetuning these models due to increasing model size continues to pose a problem. To address this challenge, prompt tuning has emerged as an alternative. However, existing works still face two problems when adapting pretrained image-text models to downstream video-text tasks: (1) The visual encoder could only encode frame-level features and failed to extract global-level general video information. (2) Equipping the visual and text encoder with separated prompts failed to mitigate the visual-text modality gap. To this end, we propose DGL, a cross-modal Dynamic prompt tuning method with Global-Local video attention. In contrast to previous prompt tuning methods, we employ the shared latent space to generate local-level text and frame prompts that encourage inter-modal interaction. Furthermore, we propose modeling video in a global-local attention mechanism to capture global video information from the perspective of prompt tuning. Extensive experiments reveal that when only 0.67% parameters are tuned, our cross-modal prompt tuning strategy DGL outperforms or is comparable to fully finetuning methods on MSR-VTT, VATEX, LSMDC, and ActivityNet datasets. Code will be available at https://github.com/knightyxp/DGL.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (7) , 6540-6548
Open AccessDGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval
Text-video retrieval is a critical multi-modal task to find the most relevant video for a text query. Although pretrained models like CLIP have demonstrated impressive potential in this area, the rising cost of fully finetuning these models due to increasing model size continues to pose a problem. To address this challenge, prompt tuning has emerged as an alternative. However, existing works still face two problems when adapting pretrained image-text models to downstream video-text tasks: (1) The visual encoder could only encode frame-level features and failed to extract global-level general video information. (2) Equipping the visual and text encoder with separated prompts failed to mitigate the visual-text modality gap. To this end, we propose DGL, a cross-modal Dynamic prompt tuning method with Global-Local video attention. In contrast to previous prompt tuning methods, we employ the shared latent space to generate local-level text and frame prompts that encourage inter-modal interaction. Furthermore, we propose modeling video in a global-local attention mechanism to capture global video information from the perspective of prompt tuning. Extensive experiments reveal that when only 0.67% parameters are tuned, our cross-modal prompt tuning strategy DGL outperforms or is comparable to fully finetuning methods on MSR-VTT, VATEX, LSMDC, and ActivityNet datasets. Code will be available at https://github.com/knightyxp/DGL.
- 14 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 4271-4280
SKIM: Skeleton-Based Isolated Sign Language Recognition With Part Mixing
In this article, we present skeleton-based isolated sign language recognition (IsoSLR) with part mixing - SKIM. An IsoSLR model that solely takes the skeleton representation of the human body as input. Previous skeleton-based works either perform worse when compared to RGB-based counterparts or require fusion with other modalities to obtain competitive results. With SKIM, a single skeleton-based model without complex pre-training can obtain similar or even higher accuracy than current state-of-the-art methods. This margin can be further increased by simple late fusion within the same modality. To achieve this, we first develop a novel data augmentation technique called part mixing. It swaps the corresponding keypoints within one region (e.g. hand) between two randomly selected samples and combines their labels linearly as the new label. As regions like hand and face are key articulators for sign language, direct swapping of such parts creates a believable pseudo sign that promotes the model to recognize the true pairs. Secondly, following current advances in skeleton-based action recognition, we devise a channel-wise graph neural network with multi-scale awareness and per-keypoint temporal re-weighting. With this design, the backbone is capable of leveraging both manual and non-manual features. The combination of hand mixing and the channel-wise multi-scale GCN backbone allows us to achieve state-of-the-art accuracy on both WLASL and NMFs-CSL benchmarks.
- 14 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 4271-4280
SKIM: Skeleton-Based Isolated Sign Language Recognition With Part Mixing
In this article, we present skeleton-based isolated sign language recognition (IsoSLR) with part mixing - SKIM. An IsoSLR model that solely takes the skeleton representation of the human body as input. Previous skeleton-based works either perform worse when compared to RGB-based counterparts or require fusion with other modalities to obtain competitive results. With SKIM, a single skeleton-based model without complex pre-training can obtain similar or even higher accuracy than current state-of-the-art methods. This margin can be further increased by simple late fusion within the same modality. To achieve this, we first develop a novel data augmentation technique called part mixing. It swaps the corresponding keypoints within one region (e.g. hand) between two randomly selected samples and combines their labels linearly as the new label. As regions like hand and face are key articulators for sign language, direct swapping of such parts creates a believable pseudo sign that promotes the model to recognize the true pairs. Secondly, following current advances in skeleton-based action recognition, we devise a channel-wise graph neural network with multi-scale awareness and per-keypoint temporal re-weighting. With this design, the backbone is capable of leveraging both manual and non-manual features. The combination of hand mixing and the channel-wise multi-scale GCN backbone allows us to achieve state-of-the-art accuracy on both WLASL and NMFs-CSL benchmarks.
- Open Access
DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval
Text-video retrieval is a critical multi-modal task to find the most relevant video for a text query. Although pretrained models like CLIP have demonstrated impressive potential in this area, the rising cost of fully finetuning these models due to increasing model size continues to pose a problem. To address this challenge, prompt tuning has emerged as an alternative. However, existing works still face two problems when adapting pretrained image-text models to downstream video-text tasks: (1) The visual encoder could only encode frame-level features and failed to extract global-level general video information. (2) Equipping the visual and text encoder with separated prompts failed to mitigate the visual-text modality gap. To this end, we propose DGL, a cross-modal Dynamic prompt tuning method with Global-Local video attention. In contrast to previous prompt tuning methods, we employ the shared latent space to generate local-level text and frame prompts that encourage inter-modal interaction. Furthermore, we propose modeling video in a global-local attention mechanism to capture global video information from the perspective of prompt tuning. Extensive experiments reveal that when only 0.67% parameters are tuned, our cross-modal prompt tuning strategy DGL outperforms or is comparable to fully finetuning methods on MSR-VTT, VATEX, LSMDC, and ActivityNet datasets. Code will be available at https://github.com/knightyxp/DGL
Open AccessDGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval
Text-video retrieval is a critical multi-modal task to find the most relevant video for a text query. Although pretrained models like CLIP have demonstrated impressive potential in this area, the rising cost of fully finetuning these models due to increasing model size continues to pose a problem. To address this challenge, prompt tuning has emerged as an alternative. However, existing works still face two problems when adapting pretrained image-text models to downstream video-text tasks: (1) The visual encoder could only encode frame-level features and failed to extract global-level general video information. (2) Equipping the visual and text encoder with separated prompts failed to mitigate the visual-text modality gap. To this end, we propose DGL, a cross-modal Dynamic prompt tuning method with Global-Local video attention. In contrast to previous prompt tuning methods, we employ the shared latent space to generate local-level text and frame prompts that encourage inter-modal interaction. Furthermore, we propose modeling video in a global-local attention mechanism to capture global video information from the perspective of prompt tuning. Extensive experiments reveal that when only 0.67% parameters are tuned, our cross-modal prompt tuning strategy DGL outperforms or is comparable to fully finetuning methods on MSR-VTT, VATEX, LSMDC, and ActivityNet datasets. Code will be available at https://github.com/knightyxp/DGL
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (5) , 3334-3350
Learning to Follow and Generate Instructions for Language-Capable Navigation
Visual-language navigation (VLN) is a challenging task that requires embodied agents to follow natural language instructions to navigate in previously unseen environments. However, existing literature put most emphasis on interpreting instructions into actions, only delivering “dumb” wayfinding agents which cannot actively use natural language to communicate with humans. In this article, we devise Lana , a language-capable n avigation a gent which is able to not only execute human-written navigation commands, but also provide route descriptions to humans. This is achieved by simultaneously learning instruction following and generation with only one single model. More specifically, two encoders, respectively for route and language encoding, are built and shared by two decoders, respectively, for action prediction and instruction generation, so as to exploit cross-task knowledge and capture task-specific characteristics. Throughout pretraining and fine-tuning, both instruction following and generation are set as optimization objectives. We further extend Lana by exploiting object semantics during route encoding. This leads to Lana+ , a more powerful framework that simulates the way humans refer to landmarks for instructions composition and wayfinding. We empirically verify that, compared with recent advanced task-specific solutions, Lana attains better performances on both instruction following and generation, with nearly half complexity. In addition, endowed with language generation capability, Lana can explain to humans its behaviors and assist human's wayfinding. Benefiting from landmark information, Lana+ exhibits even more impressive performance. This work is expected to foster future efforts towards building more trustworthy and socially-intelligent navigation robots.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (5) , 3334-3350
Learning to Follow and Generate Instructions for Language-Capable Navigation
Visual-language navigation (VLN) is a challenging task that requires embodied agents to follow natural language instructions to navigate in previously unseen environments. However, existing literature put most emphasis on interpreting instructions into actions, only delivering “dumb” wayfinding agents which cannot actively use natural language to communicate with humans. In this article, we devise Lana , a language-capable n avigation a gent which is able to not only execute human-written navigation commands, but also provide route descriptions to humans. This is achieved by simultaneously learning instruction following and generation with only one single model. More specifically, two encoders, respectively for route and language encoding, are built and shared by two decoders, respectively, for action prediction and instruction generation, so as to exploit cross-task knowledge and capture task-specific characteristics. Throughout pretraining and fine-tuning, both instruction following and generation are set as optimization objectives. We further extend Lana by exploiting object semantics during route encoding. This leads to Lana+ , a more powerful framework that simulates the way humans refer to landmarks for instructions composition and wayfinding. We empirically verify that, compared with recent advanced task-specific solutions, Lana attains better performances on both instruction following and generation, with nearly half complexity. In addition, endowed with language generation capability, Lana can explain to humans its behaviors and assist human's wayfinding. Benefiting from landmark information, Lana+ exhibits even more impressive performance. This work is expected to foster future efforts towards building more trustworthy and socially-intelligent navigation robots.
- 5 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 4389-4400
IcoCap: Improving Video Captioning by Compounding Images
Video captioning is a more challenging task compared to image captioning, primarily due to differences in content density. Video data contains redundant visual content, making it difficult for captioners to generalize diverse content and avoid being misled by irrelevant elements. Moreover, redundant content is not well-trimmed to match the corresponding visual semantics in the ground truth, further increasing the difficulty of video captioning. Current research in video captioning predominantly focuses on captioner design, neglecting the impact of content density on captioner performance. Considering the differences between videos and images, there exists an another line to improve video captioning by leveraging concise and easily-learned image samples to further diversify video samples. This modification to content density compels the captioner to learn more effectively against redundancy and ambiguity. In this paper, we propose a novel approach called I mage- Co mpounded learning for video Cap tioners (IcoCap) to facilitate better learning of complex video semantics. IcoCap comprises two components: the Image-Video Compounding Strategy (ICS) and Visual-Semantic Guided Captioning (VGC). ICS compounds easily-learned image semantics into video semantics, further diversifying video content and prompting the network to generalize contents in a more diverse sample. Besides, learning with the sample compounded with image contents, the captioner is compelled to better extract valuable video cues in the presence of straightforward image semantics. This helps the captioner further focus on relevant information while filtering out extraneous content. Then, VGC guides the network in flexibly learning ground truth captions based on the compounded samples, helping to mitigate the mismatch between the ground truth and ambiguous semantics in video samples. Our experimental results demonstrate the effectiveness of IcoCap in improving the learning of video captioners. Applied to the widely-used MSVD, MSR-VTT, and VATEX datasets, our approach achieves competitive or superior results compared to state-of-the-art methods, illustrating its capacity to handle the redundant and ambiguous video data.
- 5 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 4389-4400
IcoCap: Improving Video Captioning by Compounding Images
Video captioning is a more challenging task compared to image captioning, primarily due to differences in content density. Video data contains redundant visual content, making it difficult for captioners to generalize diverse content and avoid being misled by irrelevant elements. Moreover, redundant content is not well-trimmed to match the corresponding visual semantics in the ground truth, further increasing the difficulty of video captioning. Current research in video captioning predominantly focuses on captioner design, neglecting the impact of content density on captioner performance. Considering the differences between videos and images, there exists an another line to improve video captioning by leveraging concise and easily-learned image samples to further diversify video samples. This modification to content density compels the captioner to learn more effectively against redundancy and ambiguity. In this paper, we propose a novel approach called I mage- Co mpounded learning for video Cap tioners (IcoCap) to facilitate better learning of complex video semantics. IcoCap comprises two components: the Image-Video Compounding Strategy (ICS) and Visual-Semantic Guided Captioning (VGC). ICS compounds easily-learned image semantics into video semantics, further diversifying video content and prompting the network to generalize contents in a more diverse sample. Besides, learning with the sample compounded with image contents, the captioner is compelled to better extract valuable video cues in the presence of straightforward image semantics. This helps the captioner further focus on relevant information while filtering out extraneous content. Then, VGC guides the network in flexibly learning ground truth captions based on the compounded samples, helping to mitigate the mismatch between the ground truth and ambiguous semantics in video samples. Our experimental results demonstrate the effectiveness of IcoCap in improving the learning of video captioners. Applied to the widely-used MSVD, MSR-VTT, and VATEX datasets, our approach achieves competitive or superior results compared to state-of-the-art methods, illustrating its capacity to handle the redundant and ambiguous video data.