Jiaqi Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiaqi Wang has a total of 60 co-authors. Here are the top co-authors by number of shared publications:
- Dahua Lin
The Chinese University of Hong Kong, Hong Kong, China
5 shared publications - Chen Change Loy
S-Lab, Nanyang Technological University, Singapore, Singapore
4 shared publications Kai Chen
Information Engineering, The Chinese University of Hong Kong, 26451 Hong Kong, Hong Kong, Hong Kong
3 shared publications- Wenwei Zhang
Shanghai AI Laboratory, Shanghai, China
3 shared publications Dahua Lin
Information Engineering, The Chinese University of Hong Kong, 26451 Hong Kong, Hong Kong, Hong Kong
2 shared publicationsJiangmiao Pang
Zhejiang University
2 shared publications
Latest Publications
- 10 September 2026
- Published by Springer Nature
- p. 147-164
Perceptual Projection Pruning: Diversity-Aware Video Token Pruning for Multimodal Large Language Models
- 10 September 2026
- Published by Springer Nature
- p. 147-164
Perceptual Projection Pruning: Diversity-Aware Video Token Pruning for Multimodal Large Language Models
- 9 September 2026
- Published by Springer Nature
- p. 287-304
UniREditBench: A Unified Reasoning-Based Image Editing Benchmark
- 9 September 2026
- Published by Springer Nature
- p. 287-304
UniREditBench: A Unified Reasoning-Based Image Editing Benchmark
- Top Cited Papers
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 388-401
RAR: Retrieving and Ranking Augmented MLLMs for Visual Recognition
CLIP (Contrastive Language–Image Pre-training) uses contrastive learning from noise image-text pairs to excel at recognizing a wide array of candidates, yet its focus on broad associations hinders the precision in distinguishing subtle differences among fine-grained items. Conversely, Multimodal Large Language Models (MLLMs) excel at classifying fine-grained categories, thanks to their substantial knowledge from pre-training on web-level corpora. However, the performance of MLLMs declines with an increase in category numbers, primarily due to growing complexity and constraints of limited context window size. To synergize the strengths of both approaches and enhance the few-shot/zero-shot recognition abilities for datasets characterized by extensive and fine-grained vocabularies, this paper introduces RAR, a Retrieving And Ranking augmented method for MLLMs. We initially establish a multi-modal retriever based on CLIP to create and store explicit memory for different categories beyond the immediate context window. During inference, RAR retrieves the top-k similar results from the memory and uses MLLMs to rank and make the final predictions. Our proposed approach not only addresses the inherent limitations in fine-grained recognition but also preserves the models comprehensive knowledge base, significantly boosting accuracy across a range of vision-language recognition tasks. Notably, our approach demonstrates a significant improvement in performance on 5 fine-grained visual recognition benchmarks, 11 few-shot image recognition datasets, and the 2 object detection datasets under the zero-shot recognition setting.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 388-401
Top Cited PapersRAR: Retrieving and Ranking Augmented MLLMs for Visual Recognition
CLIP (Contrastive Language–Image Pre-training) uses contrastive learning from noise image-text pairs to excel at recognizing a wide array of candidates, yet its focus on broad associations hinders the precision in distinguishing subtle differences among fine-grained items. Conversely, Multimodal Large Language Models (MLLMs) excel at classifying fine-grained categories, thanks to their substantial knowledge from pre-training on web-level corpora. However, the performance of MLLMs declines with an increase in category numbers, primarily due to growing complexity and constraints of limited context window size. To synergize the strengths of both approaches and enhance the few-shot/zero-shot recognition abilities for datasets characterized by extensive and fine-grained vocabularies, this paper introduces RAR, a Retrieving And Ranking augmented method for MLLMs. We initially establish a multi-modal retriever based on CLIP to create and store explicit memory for different categories beyond the immediate context window. During inference, RAR retrieves the top-k similar results from the memory and uses MLLMs to rank and make the final predictions. Our proposed approach not only addresses the inherent limitations in fine-grained recognition but also preserves the models comprehensive knowledge base, significantly boosting accuracy across a range of vision-language recognition tasks. Notably, our approach demonstrates a significant improvement in performance on 5 fine-grained visual recognition benchmarks, 11 few-shot image recognition datasets, and the 2 object detection datasets under the zero-shot recognition setting.
- Open Access
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (6) , 1-12
SS4D: Native 4D Generative Model via Structured Spacetime Latents
We present SS4D, a native 4D generative model that synthesizes dynamic 3D objects directly from monocular video. Unlike prior approaches that construct 4D representations by optimizing over 3D or video generative models, we train a generator directly on 4D data, achieving high fidelity, temporal coherence, and structural consistency. At the core of our method is a compressed set of structured spacetime latents. Specifically, (1) To address the scarcity of 4D training data, we build on a pre-trained single-image-to-3D model, preserving strong spatial consistency. (2) Temporal consistency is enforced by introducing dedicated temporal layers that reason across frames. (3) To support efficient training and inference over long video sequences, we compress the latent sequence along the temporal axis using factorized 4D convolutions and temporal downsampling blocks. In addition, we employ a carefully designed training strategy to enhance robustness against occlusion and motion blur, leading to high-quality generation. Extensive experiments show that SS4D produces spatio-temporally consistent 4D objects with superior quality and efficiency, significantly outperforming state-of-the-art methods on both synthetic and real-world datasets.
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (6) , 1-12
Open AccessSS4D: Native 4D Generative Model via Structured Spacetime Latents
We present SS4D, a native 4D generative model that synthesizes dynamic 3D objects directly from monocular video. Unlike prior approaches that construct 4D representations by optimizing over 3D or video generative models, we train a generator directly on 4D data, achieving high fidelity, temporal coherence, and structural consistency. At the core of our method is a compressed set of structured spacetime latents. Specifically, (1) To address the scarcity of 4D training data, we build on a pre-trained single-image-to-3D model, preserving strong spatial consistency. (2) Temporal consistency is enforced by introducing dedicated temporal layers that reason across frames. (3) To support efficient training and inference over long video sequences, we compress the latent sequence along the temporal axis using factorized 4D convolutions and temporal downsampling blocks. In addition, we employ a carefully designed training strategy to enhance robustness against occlusion and motion blur, leading to high-quality generation. Extensive experiments show that SS4D produces spatio-temporally consistent 4D objects with superior quality and efficiency, significantly outperforming state-of-the-art methods on both synthetic and real-world datasets.
- 25 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (7) , 5238-5255
Language-Aware Vision Transformer for Referring Segmentation
Referring segmentation is a fundamental vision-language task that aims to segment out an object from an image or video in accordance with a natural language description. One of the key challenges behind this task is leveraging the referring expression for highlighting relevant positions in the image or video frames. A paradigm for tackling this problem in both the image and the video domains is to leverage a powerful vision-language (“cross-modal”) decoder to fuse features independently extracted from a vision encoder and a language encoder. Recent methods have made remarkable advances in this paradigm by exploiting Transformers as cross-modal decoders, concurrent to the Transformer’s overwhelming success in many other vision-language tasks. Adopting a different approach in this work, we show that significantly better cross-modal alignments can be achieved through the early fusion of linguistic and visual features in intermediate layers of a vision Transformer encoder network. Based on the idea of conducting cross-modal feature fusion in the visual feature encoding stage, we propose a unified framework named Language-Aware Vision Transformer (LAVT), which leverages the well-proven correlation modeling power of a Transformer encoder for excavating helpful multi-modal context. This way, accurate segmentation results can be harvested with a light-weight mask predictor. One of the key components in the proposed system is a dense attention mechanism for collecting pixel-specific linguistic cues. When dealing with video inputs, we present the video LAVT framework and design a 3D version of this component by introducing multi-scale convolutional operators arranged in a parallel fashion, which can exploit spatio-temporal dependencies at different granularity levels. We further introduce unified LAVT as a unified framework that could handle both image and video inputs with enhanced segmentation capability on unified referring segmentation task. Our methods surpass previous state-of-the-art methods on seven benchmarks for referring image segmentation and referring video segmentation. The code to reproduce our experiments is available at LAVT-RS.
- 25 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (7) , 5238-5255
Language-Aware Vision Transformer for Referring Segmentation
Referring segmentation is a fundamental vision-language task that aims to segment out an object from an image or video in accordance with a natural language description. One of the key challenges behind this task is leveraging the referring expression for highlighting relevant positions in the image or video frames. A paradigm for tackling this problem in both the image and the video domains is to leverage a powerful vision-language (“cross-modal”) decoder to fuse features independently extracted from a vision encoder and a language encoder. Recent methods have made remarkable advances in this paradigm by exploiting Transformers as cross-modal decoders, concurrent to the Transformer’s overwhelming success in many other vision-language tasks. Adopting a different approach in this work, we show that significantly better cross-modal alignments can be achieved through the early fusion of linguistic and visual features in intermediate layers of a vision Transformer encoder network. Based on the idea of conducting cross-modal feature fusion in the visual feature encoding stage, we propose a unified framework named Language-Aware Vision Transformer (LAVT), which leverages the well-proven correlation modeling power of a Transformer encoder for excavating helpful multi-modal context. This way, accurate segmentation results can be harvested with a light-weight mask predictor. One of the key components in the proposed system is a dense attention mechanism for collecting pixel-specific linguistic cues. When dealing with video inputs, we present the video LAVT framework and design a 3D version of this component by introducing multi-scale convolutional operators arranged in a parallel fashion, which can exploit spatio-temporal dependencies at different granularity levels. We further introduce unified LAVT as a unified framework that could handle both image and video inputs with enhanced segmentation capability on unified referring segmentation task. Our methods surpass previous state-of-the-art methods on seven benchmarks for referring image segmentation and referring video segmentation. The code to reproduce our experiments is available at LAVT-RS.
- Open Access
- 10 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-10
HyperDreamer: Hyper-Realistic 3D Content Generation and Editing from a Single Image
3D content creation from a single image is a long-standing yet highly desirable task. Recent advances introduce 2D diffusion priors, yielding reasonable results. However, existing methods are not hyper-realistic enough for post-generation usage, as users cannot view, render and edit the resulting 3D content from a full range. To address these challenges, we introduce HyperDreamer with several key designs and appealing properties: 1) Full-range viewable: 360° mesh modeling with high-resolution textures enables the creation of visually compelling 3D models from a full range of observation points. 2) Full-range renderable: Fine-grained semantic segmentation and data-driven priors are incorporated as guidance to learn reasonable albedo, roughness, and specular properties of the materials, enabling semantic-aware arbitrary material estimation. 3) Full-range editable: For a generated model or their own data, users can interactively select any region via a few clicks and efficiently edit the texture with text-based guidance. Extensive experiments demonstrate the effectiveness of HyperDreamer in modeling region-aware materials with high-resolution textures and enabling user-friendly editing. We believe that HyperDreamer holds promise for advancing 3D content creation and finding applications in various domains.
- 10 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessHyperDreamer: Hyper-Realistic 3D Content Generation and Editing from a Single Image
3D content creation from a single image is a long-standing yet highly desirable task. Recent advances introduce 2D diffusion priors, yielding reasonable results. However, existing methods are not hyper-realistic enough for post-generation usage, as users cannot view, render and edit the resulting 3D content from a full range. To address these challenges, we introduce HyperDreamer with several key designs and appealing properties: 1) Full-range viewable: 360° mesh modeling with high-resolution textures enables the creation of visually compelling 3D models from a full range of observation points. 2) Full-range renderable: Fine-grained semantic segmentation and data-driven priors are incorporated as guidance to learn reasonable albedo, roughness, and specular properties of the materials, enabling semantic-aware arbitrary material estimation. 3) Full-range editable: For a generated model or their own data, users can interactively select any region via a few clicks and efficiently edit the texture with text-based guidance. Extensive experiments demonstrate the effectiveness of HyperDreamer in modeling region-aware materials with high-resolution textures and enabling user-friendly editing. We believe that HyperDreamer holds promise for advancing 3D content creation and finding applications in various domains.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5302-5310
Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5302-5310
Open AccessZero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization
- 1 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 30 (10577149) , 9112-9124
Texture Memory-Augmented Deep Patch-Based Image Inpainting
Patch-based methods and deep networks have been employed to tackle image inpainting problem, with their own strengths and weaknesses. Patch-based methods are capable of restoring a missing region with high-quality texture through searching nearest neighbor patches from the unmasked regions. However, these methods bring problematic contents when recovering large missing regions. Deep networks, on the other hand, show promising results in completing large regions. Nonetheless, the results often lack faithful and sharp details that resemble the surrounding area. By bringing together the best of both paradigms, we propose a new deep inpainting framework where texture generation is guided by a texture memory of patch samples extracted from unmasked regions. The framework has a novel design that allows texture memory retrieval to be trained end-to-end with the deep inpainting network. In addition, we introduce a patch distribution loss to encourage high-quality patch synthesis. The proposed method shows superior performance both qualitatively and quantitatively on three challenging image benchmarks, i.e., Places, CelebA-HQ, and Paris Street-View datasets (Code will be made publicly available in https://github.com/open-mmlab/mmediting ).
- 1 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 30 (10577149) , 9112-9124
Texture Memory-Augmented Deep Patch-Based Image Inpainting
Patch-based methods and deep networks have been employed to tackle image inpainting problem, with their own strengths and weaknesses. Patch-based methods are capable of restoring a missing region with high-quality texture through searching nearest neighbor patches from the unmasked regions. However, these methods bring problematic contents when recovering large missing regions. Deep networks, on the other hand, show promising results in completing large regions. Nonetheless, the results often lack faithful and sharp details that resemble the surrounding area. By bringing together the best of both paradigms, we propose a new deep inpainting framework where texture generation is guided by a texture memory of patch samples extracted from unmasked regions. The framework has a novel design that allows texture memory retrieval to be trained end-to-end with the deep inpainting network. In addition, we introduce a patch distribution loss to encourage high-quality patch synthesis. The proposed method shows superior performance both qualitatively and quantitatively on three challenging image benchmarks, i.e., Places, CelebA-HQ, and Paris Street-View datasets (Code will be made publicly available in https://github.com/open-mmlab/mmediting ).
- Open Access
Seesaw Loss for Long-Tailed Instance Segmentation
Instance segmentation has witnessed a remarkable progress on class-balanced benchmarks. However, they fail to perform as accurately in real-world scenarios, where the category distribution of objects naturally comes with a long tail. Instances of head classes dominate a long-tailed dataset and they serve as negative samples of tail categories. The overwhelming gradients of negative samples on tail classes lead to a biased learning process for classifiers. Consequently, objects of tail categories are more likely to be misclassified as backgrounds or head categories. To tackle this problem, we propose Seesaw Loss to dynamically re-balance gradients of positive and negative samples for each category, with two complementary factors, i.e., mitigation factor and compensation factor. The mitigation factor reduces punishments to tail categories w.r.t. the ratio of cumulative training instances between different categories. Meanwhile, the compensation factor increases the penalty of misclassified instances to avoid false positives of tail categories. We conduct extensive experiments on Seesaw Loss with mainstream frameworks and different data sampling strategies. With a simple end-to-end training pipeline, Seesaw Loss obtains significant gains over Cross-Entropy Loss, and achieves state-of-the-art performance on LVIS dataset without bells and whistles. Code is available at https://github.com/open-mmlab/mmdetection.
Open AccessSeesaw Loss for Long-Tailed Instance Segmentation
Instance segmentation has witnessed a remarkable progress on class-balanced benchmarks. However, they fail to perform as accurately in real-world scenarios, where the category distribution of objects naturally comes with a long tail. Instances of head classes dominate a long-tailed dataset and they serve as negative samples of tail categories. The overwhelming gradients of negative samples on tail classes lead to a biased learning process for classifiers. Consequently, objects of tail categories are more likely to be misclassified as backgrounds or head categories. To tackle this problem, we propose Seesaw Loss to dynamically re-balance gradients of positive and negative samples for each category, with two complementary factors, i.e., mitigation factor and compensation factor. The mitigation factor reduces punishments to tail categories w.r.t. the ratio of cumulative training instances between different categories. Meanwhile, the compensation factor increases the penalty of misclassified instances to avoid false positives of tail categories. We conduct extensive experiments on Seesaw Loss with mainstream frameworks and different data sampling strategies. With a simple end-to-end training pipeline, Seesaw Loss obtains significant gains over Cross-Entropy Loss, and achieves state-of-the-art performance on LVIS dataset without bells and whistles. Code is available at https://github.com/open-mmlab/mmdetection.
- 21 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (01628828) , 1
CARAFE++: Unified Content-Aware ReAssembly of FEatures
Feature reassembly, i.e. feature downsampling and upsampling, is a key operation in a number of modern convolutional network architectures, e.g., residual networks and feature pyramids. Its design is critical for dense prediction tasks such as object detection and semantic/instance segmentation. In this work, we propose unified Content-Aware ReAssembly of FEatures (CARAFE++), a universal, lightweight, and highly effective operator to fulfill this goal. CARAFE++ has several appealing properties: (1) Unlike conventional methods such as pooling and interpolation that only exploit sub-pixel neighborhood, CARAFE++ aggregates contextual information within a large receptive field. (2) Instead of using a fixed kernel for all samples (e.g. convolution and deconvolution), CARAFE++ generates adaptive kernels on-the-fly to enable instance-specific content-aware handling. (3) CARAFE++ introduces little computational overhead and can be readily integrated into modern network architectures. We conduct comprehensive evaluations on standard benchmarks in object detection, instance/semantic segmentation, and image inpainting. CARAFE++ shows consistent and substantial gains on mainstream methods across all the tasks with negligible computational overhead. It shows great potential to serve as a strong building block for modern deep networks.
- 21 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (01628828) , 1
CARAFE++: Unified Content-Aware ReAssembly of FEatures
Feature reassembly, i.e. feature downsampling and upsampling, is a key operation in a number of modern convolutional network architectures, e.g., residual networks and feature pyramids. Its design is critical for dense prediction tasks such as object detection and semantic/instance segmentation. In this work, we propose unified Content-Aware ReAssembly of FEatures (CARAFE++), a universal, lightweight, and highly effective operator to fulfill this goal. CARAFE++ has several appealing properties: (1) Unlike conventional methods such as pooling and interpolation that only exploit sub-pixel neighborhood, CARAFE++ aggregates contextual information within a large receptive field. (2) Instead of using a fixed kernel for all samples (e.g. convolution and deconvolution), CARAFE++ generates adaptive kernels on-the-fly to enable instance-specific content-aware handling. (3) CARAFE++ introduces little computational overhead and can be readily integrated into modern network architectures. We conduct comprehensive evaluations on standard benchmarks in object detection, instance/semantic segmentation, and image inpainting. CARAFE++ shows consistent and substantial gains on mainstream methods across all the tasks with negligible computational overhead. It shows great potential to serve as a strong building block for modern deep networks.