Yu Yin
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
Yu Yin has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Yun Fu
Northeastern University, USA
6 shared publications - Yiren Lu
Department of Computer and Data Sciences, Case Western Reserve University, Cleveland, OH, USA
4 shared publications - Jing Ma
Case Western Reserve University
3 shared publications - Disheng Liu
Department of Computer and Data Sciences, Case Western Reserve University
2 shared publications - Joseph Peter Robinson
Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA
2 shared publications - Lichen Wang
Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16104-16112
Filling the Unseen: Holistic Scene Extrapolation via 3D Gaussian Splatting
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16104-16112
Open AccessFilling the Unseen: Holistic Scene Extrapolation via 3D Gaussian Splatting
- 5 October 2026
- Published by Springer Nature
- p. 663-681
DefenseSplat: Enhancing the Robustness of 3D Gaussian Splatting via Frequency-Aware Filtering
- 5 October 2026
- Published by Springer Nature
- p. 663-681
DefenseSplat: Enhancing the Robustness of 3D Gaussian Splatting via Frequency-Aware Filtering
- 29 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP  (01628828) , 1-15
When ‘YES’ Meets ‘but’: Can AI Comprehend Contradictory Humor in Comics?
Understanding humor, especially when it involves complex and contradictory narratives requiring comparative reasoning ability, remains a significant challenge for large vision language models (VLMs). This limitation hinders AI's ability to engage in human-like reasoning and cultural expression. In this paper, we investigate this challenge through an in depth analysis of comics that juxtapose panels to create humor through contradictions. We introduce the YESBUT, a novel benchmark with 1,262 comic images from diverse multilingual and multicultural contexts, featuring comprehensive annotations that capture various aspects of narrative understanding. Using this benchmark, we systematically evaluate a wide range of VLMs through four complementary tasks spanning from surface content comprehension to deep narrative reasoning, with particular emphasis on comparative reasoning between contradictory elements. Our extensive experiments reveal that even the most advanced models significantly underperform compared to humans, with common failures in visual perception, key element identification, comparative analysis, and hallucinations. We further investigate text-based training strategies and social knowledge augmentation methods to enhance model performance. Our findings not only highlight critical weaknesses in VLMs' understanding of cultural and creative expressions but also provide pathways toward developing context-aware models capable of deeper narrative understanding through comparative reasoning.
- 29 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP  (01628828) , 1-15
When ‘YES’ Meets ‘but’: Can AI Comprehend Contradictory Humor in Comics?
Understanding humor, especially when it involves complex and contradictory narratives requiring comparative reasoning ability, remains a significant challenge for large vision language models (VLMs). This limitation hinders AI's ability to engage in human-like reasoning and cultural expression. In this paper, we investigate this challenge through an in depth analysis of comics that juxtapose panels to create humor through contradictions. We introduce the YESBUT, a novel benchmark with 1,262 comic images from diverse multilingual and multicultural contexts, featuring comprehensive annotations that capture various aspects of narrative understanding. Using this benchmark, we systematically evaluate a wide range of VLMs through four complementary tasks spanning from surface content comprehension to deep narrative reasoning, with particular emphasis on comparative reasoning between contradictory elements. Our extensive experiments reveal that even the most advanced models significantly underperform compared to humans, with common failures in visual perception, key element identification, comparative analysis, and hallucinations. We further investigate text-based training strategies and social knowledge augmentation methods to enhance model performance. Our findings not only highlight critical weaknesses in VLMs' understanding of cultural and creative expressions but also provide pathways toward developing context-aware models capable of deeper narrative understanding through comparative reasoning.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3597-3606
View-consistent Object Removal in Radiance Fields
Radiance Fields (RFs) have emerged as a crucial technology for 3D scene representation, enabling the synthesis of novel views with remarkable realism. However, as RFs become more widely used, the need for effective editing techniques that maintain coherence across different perspectives becomes evident. Current methods primarily depend on per-frame 2D image inpainting, which often fails to maintain consistency across views, thus compromising the realism of edited RF scenes. In this work, we introduce a novel RF editing pipeline that significantly enhances consistency by requiring the inpainting of only a single reference image. This image is then projected across multiple views using a depth-based approach, effectively reducing the inconsistencies observed with per-frame inpainting. However, projections typically assume photometric consistency across views, which is often impractical in real-world settings. To accommodate realistic variations in lighting and viewpoint, our pipeline adjusts the appearance of the projected views by generating multiple directional variants of the inpainted image, thereby adapting to different photometric conditions. Additionally, we present an effective and robust multi-view object segmentation approach as a valuable byproduct of our pipeline. Extensive experiments demonstrate that our method significantly surpasses existing frameworks in maintaining content consistency across views and enhancing visual quality. More results are available at https://vulab-ai.github.io/View-consistent_Object_Removal_in_Radiance_Fields/.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3597-3606
Open AccessView-consistent Object Removal in Radiance Fields
Radiance Fields (RFs) have emerged as a crucial technology for 3D scene representation, enabling the synthesis of novel views with remarkable realism. However, as RFs become more widely used, the need for effective editing techniques that maintain coherence across different perspectives becomes evident. Current methods primarily depend on per-frame 2D image inpainting, which often fails to maintain consistency across views, thus compromising the realism of edited RF scenes. In this work, we introduce a novel RF editing pipeline that significantly enhances consistency by requiring the inpainting of only a single reference image. This image is then projected across multiple views using a depth-based approach, effectively reducing the inconsistencies observed with per-frame inpainting. However, projections typically assume photometric consistency across views, which is often impractical in real-world settings. To accommodate realistic variations in lighting and viewpoint, our pipeline adjusts the appearance of the projected views by generating multiple directional variants of the inpainted image, thereby adapting to different photometric conditions. Additionally, we present an effective and robust multi-view object segmentation approach as a valuable byproduct of our pipeline. Extensive experiments demonstrate that our method significantly surpasses existing frameworks in maintaining content consistency across views and enhancing visual quality. More results are available at https://vulab-ai.github.io/View-consistent_Object_Removal_in_Radiance_Fields/.
- 22 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32  (10577149) , 524-536
Human Motion Segmentation via Velocity-Sensitive Dual-Side Auto-Encoder
Human motion segmentation (HMS) aims to segment a long human action video into a bunch of short and meaningful action clips. Existing supervised learning approaches need a large amount of training data which may be costly in real-world scenario, while most unsupervised clustering methods cannot fully explore the temporal correlations among human motions and hard to achieve promising performances. In our paper, we design a novel unsupervised framework, called Velocity-Sensitive Dual-Side Auto-Encoder (VSDA), for HMS task. Specifically, a multi-neighbor auto-encoder (MNA) is proposed to extract informative temporal features, which fully explores the local temporal patterns of human motions. In addition, a long-short distance encoding (LSE) strategy is designed. It constrains the encoded representations of close (short-distance) frames becoming similar while the representations of far-away (long-distance) frames becoming distinctive. Similarly, this strategy is also deployed on the decoded outputs as the long-short distance decoding (LSD) module. The LSE/LSD guides the learning process explicitly and implicitly to achieve the dual-side structure. Moreover, we consider the energy variations during the human motion to propose the velocity-sensitive (VS) guidance mechanism for further model improvement. VSDA leverages the temporal characteristics of human motion and derives promising HMS performance. Comprehensive experiments on six real-world human motion datasets illustrate the effectiveness of our proposed model.
- 22 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32  (10577149) , 524-536
Human Motion Segmentation via Velocity-Sensitive Dual-Side Auto-Encoder
Human motion segmentation (HMS) aims to segment a long human action video into a bunch of short and meaningful action clips. Existing supervised learning approaches need a large amount of training data which may be costly in real-world scenario, while most unsupervised clustering methods cannot fully explore the temporal correlations among human motions and hard to achieve promising performances. In our paper, we design a novel unsupervised framework, called Velocity-Sensitive Dual-Side Auto-Encoder (VSDA), for HMS task. Specifically, a multi-neighbor auto-encoder (MNA) is proposed to extract informative temporal features, which fully explores the local temporal patterns of human motions. In addition, a long-short distance encoding (LSE) strategy is designed. It constrains the encoded representations of close (short-distance) frames becoming similar while the representations of far-away (long-distance) frames becoming distinctive. Similarly, this strategy is also deployed on the decoded outputs as the long-short distance decoding (LSD) module. The LSE/LSD guides the learning process explicitly and implicitly to achieve the dual-side structure. Moreover, we consider the energy variations during the human motion to propose the velocity-sensitive (VS) guidance mechanism for further model improvement. VSDA leverages the temporal characteristics of human motion and derives promising HMS performance. Comprehensive experiments on six real-world human motion datasets illustrate the effectiveness of our proposed model.
- Open Access
NeRFInvertor: High Fidelity NeRF-GAN Inversion for Single-shot Real Image Animation
Nerf-based Generative models have shown impressive capacity in generating high-quality images with consistent 3D geometry. Despite successful synthesis of fake identity images randomly sampled from latent space, adopting these models for generating face images of real subjects is still a challenging task due to its so-called inversion issue. In this paper, we propose a universal method to surgically fine-tune these NeRF-GAN models in order to achieve high-fidelity animation of real subjects only by a single image. Given the optimized latent code for an out-of-domain real image, we employ 2D loss functions on the rendered image to reduce the identity gap. Furthermore, our method leverages explicit and implicit 3D regularizations using the in-domain neighborhood samples around the optimized latent code to remove geometrical and visual artifacts. Our experiments confirm the effectiveness of our method in realistic, high-fidelity, and 3D consistent animation of real faces on multiple NeRF-GAN models across different datasets.
Open AccessNeRFInvertor: High Fidelity NeRF-GAN Inversion for Single-shot Real Image Animation
Nerf-based Generative models have shown impressive capacity in generating high-quality images with consistent 3D geometry. Despite successful synthesis of fake identity images randomly sampled from latent space, adopting these models for generating face images of real subjects is still a challenging task due to its so-called inversion issue. In this paper, we propose a universal method to surgically fine-tune these NeRF-GAN models in order to achieve high-fidelity animation of real subjects only by a single image. Given the optimized latent code for an out-of-domain real image, we employ 2D loss functions on the rendered image to reduce the identity gap. Furthermore, our method leverages explicit and implicit 3D regularizations using the in-domain neighborhood samples around the optimized latent code to remove geometrical and visual artifacts. Our experiments confirm the effectiveness of our method in realistic, high-fidelity, and 3D consistent animation of real faces on multiple NeRF-GAN models across different datasets.
- 9 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 31  (10577149) , 7179-7190
Semi-Supervised Domain Adaptive Structure Learning
Semi-supervised domain adaptation (SSDA) is quite a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. Unfortunately, a simple combination of domain adaptation (DA) and semi-supervised learning (SSL) methods often fail to address such two objects because of training data bias towards labeled samples. In this paper, we introduce an adaptive structure learning method to regularize the cooperation of SSL and DA. Inspired by the multi-views learning, our proposed framework is composed of a shared feature encoder network and two classifier networks, trained for contradictory purposes. Among them, one of the classifiers is applied to group target features to improve intra-class density, enlarging the gap of categorical clusters for robust representation learning. Meanwhile, the other classifier, serviced as a regularizer, attempts to scatter the source features to enhance the smoothness of the decision boundary. The iterations of target clustering and source expansion make the target features being well-enclosed inside the dilated boundary of the corresponding source points. For the joint address of cross-domain features alignment and partially labeled data learning, we apply the maximum mean discrepancy (MMD) distance minimization and self-training (ST) to project the contradictory structures into a shared view to make the reliable final decision. The experimental results over the standard SSDA benchmarks, including DomainNet and Office-home, demonstrate both the accuracy and robustness of our method over the state-of-the-art approaches.
- 9 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 31  (10577149) , 7179-7190
Semi-Supervised Domain Adaptive Structure Learning
Semi-supervised domain adaptation (SSDA) is quite a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. Unfortunately, a simple combination of domain adaptation (DA) and semi-supervised learning (SSL) methods often fail to address such two objects because of training data bias towards labeled samples. In this paper, we introduce an adaptive structure learning method to regularize the cooperation of SSL and DA. Inspired by the multi-views learning, our proposed framework is composed of a shared feature encoder network and two classifier networks, trained for contradictory purposes. Among them, one of the classifiers is applied to group target features to improve intra-class density, enlarging the gap of categorical clusters for robust representation learning. Meanwhile, the other classifier, serviced as a regularizer, attempts to scatter the source features to enhance the smoothness of the decision boundary. The iterations of target clustering and source expansion make the target features being well-enclosed inside the dilated boundary of the corresponding source points. For the joint address of cross-domain features alignment and partially labeled data learning, we apply the maximum mean discrepancy (MMD) distance minimization and self-training (ST) to project the contradictory structures into a shared view to make the reliable final decision. The experimental results over the standard SSDA benchmarks, including DomainNet and Office-home, demonstrate both the accuracy and robustness of our method over the state-of-the-art approaches.
- Open Access
Context-Aware Interaction Network for Question Matching
Impressive milestones have been achieved in text matching by adopting a cross-attention mechanism to capture pertinent semantic connections between two sentence representations. However, regular cross-attention focuses on word-level links between the two input sequences, neglecting the importance of contextual information. We propose a context-aware interaction network (COIN) to properly align two sequences and infer their semantic relationship. Specifically, each interaction block includes (1) a context-aware cross-attention mechanism to effectively integrate contextual information when aligning two sequences, and (2) a gate fusion layer to flexibly interpolate aligned representations. We apply multiple stacked interaction blocks to produce alignments at different levels and gradually refine the attention results. Experiments on two question matching datasets and detailed analyses demonstrate the effectiveness of our model.
Open AccessContext-Aware Interaction Network for Question Matching
Impressive milestones have been achieved in text matching by adopting a cross-attention mechanism to capture pertinent semantic connections between two sentence representations. However, regular cross-attention focuses on word-level links between the two input sequences, neglecting the importance of contextual information. We propose a context-aware interaction network (COIN) to properly align two sequences and infer their semantic relationship. Specifically, each interaction block includes (1) a context-aware cross-attention mechanism to effectively integrate contextual information when aligning two sequences, and (2) a gate fusion layer to flexibly interpolate aligned representations. We apply multiple stacked interaction blocks to produce alignments at different levels and gradually refine the attention results. Experiments on two question matching datasets and detailed analyses demonstrate the effectiveness of our model.
- 10 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 24  (15209210) , 3582-3594
Families in Wild Multimedia: A Multimodal Database for Recognizing Kinship
Kinship is a soft biometric detectable in media with an abundance of practical applications. Despite the difficulty of detecting kinship, annual data challenges using still-images have consistently improved performances and attracted new researchers. Now, systems reach performance levels unforeseeable a decade ago, closing in on performances acceptable to deploy in practice. Similar to other biometric tasks, we expect systems can benefit from additional modalities. We hypothesize that adding modalities to FIW, which contains only still-images, will improve performance. Thus, to narrow the gap between research and reality and enhance the power of kinship recognition systems, we extend FIW with multimedia (MM) data (i.e., video, audio, and text captions). Specifically, we introduce the first publicly available multi-task MM kinship dataset. To build FIW MM, we developed machinery to automatically collect, annotate, and prepare the data, requiring minimal human input and no financial cost. The proposed MM corpus allows the problem statements to be more realistic template-based protocols. We show significant improvements in all benchmarks with the added modalities. The results highlight edge cases to inspire future research with different areas of improvement. FIW MM provides the data required to increase the potential of automated systems to detect kinship in MM. It also allows experts from diverse fields to collaborate in novel ways.
- 10 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 24  (15209210) , 3582-3594
Families in Wild Multimedia: A Multimodal Database for Recognizing Kinship
Kinship is a soft biometric detectable in media with an abundance of practical applications. Despite the difficulty of detecting kinship, annual data challenges using still-images have consistently improved performances and attracted new researchers. Now, systems reach performance levels unforeseeable a decade ago, closing in on performances acceptable to deploy in practice. Similar to other biometric tasks, we expect systems can benefit from additional modalities. We hypothesize that adding modalities to FIW, which contains only still-images, will improve performance. Thus, to narrow the gap between research and reality and enhance the power of kinship recognition systems, we extend FIW with multimedia (MM) data (i.e., video, audio, and text captions). Specifically, we introduce the first publicly available multi-task MM kinship dataset. To build FIW MM, we developed machinery to automatically collect, annotate, and prepare the data, requiring minimal human input and no financial cost. The proposed MM corpus allows the problem statements to be more realistic template-based protocols. We show significant improvements in all benchmarks with the added modalities. The results highlight edge cases to inspire future research with different areas of improvement. FIW MM provides the data required to increase the potential of automated systems to detect kinship in MM. It also allows experts from diverse fields to collaborate in novel ways.
- Open Access
Collaborative Attention Mechanism for Multi-View Action Recognition
Multi-view action recognition (MVAR) leverages complementary temporal information from different views to improve the learning performance. Obtaining informative view-specific representation plays an essential role in MVAR. Attention has been widely adopted as an effective strategy for discovering discriminative cues underlying temporal data. However, most existing MVAR methods only utilize attention to extract representation for each view individually, ignoring the potential to dig latent patterns based on mutual-support information in attention space. To this end, we propose a collaborative attention mechanism (CAM) for solving the MVAR problem in this paper. The proposed CAM detects the attention differences among multi-view, and adaptively integrates frame-level information to benefit each other. Specifically, we extend the long short-term memory (LSTM) to a Mutual-Aid RNN (MAR) to achieve the multi-view collaboration process. CAM takes advantages of view-specific attention pattern to guide another view and discover potential information which is hard to be explored by itself. It paves a novel way to leverage attention information and enhances the multi-view representation learning. Extensive experiments on four action datasets illustrate the proposed CAM achieves better results for each view and also boosts multi-view performance.
Open AccessCollaborative Attention Mechanism for Multi-View Action Recognition
Multi-view action recognition (MVAR) leverages complementary temporal information from different views to improve the learning performance. Obtaining informative view-specific representation plays an essential role in MVAR. Attention has been widely adopted as an effective strategy for discovering discriminative cues underlying temporal data. However, most existing MVAR methods only utilize attention to extract representation for each view individually, ignoring the potential to dig latent patterns based on mutual-support information in attention space. To this end, we propose a collaborative attention mechanism (CAM) for solving the MVAR problem in this paper. The proposed CAM detects the attention differences among multi-view, and adaptively integrates frame-level information to benefit each other. Specifically, we extend the long short-term memory (LSTM) to a Mutual-Aid RNN (MAR) to achieve the multi-view collaboration process. CAM takes advantages of view-specific attention pattern to guide another view and discover potential information which is hard to be explored by itself. It paves a novel way to leverage attention information and enhances the multi-view representation learning. Extensive experiments on four action datasets illustrate the proposed CAM achieves better results for each view and also boosts multi-view performance.