402 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Alibaba Group (China)CN60 papers
- Zhejiang UniversityCN46 papers
- Bellevue Hospital CenterUS30 papers
- Peking UniversityCN22 papers
- Nanyang Technological UniversitySG21 papers
- Tsinghua UniversityCN15 papers
- Chinese Academy of SciencesCN14 papers
- Renmin University of ChinaCN13 papers
- Shanghai Jiao Tong UniversityCN11 papers
- Tianjin UniversityCN11 papers
- Alibaba Group (Cayman Islands)KY10 papers
- East China Normal UniversityCN10 papers
89 papers · 1 filter
CompAdapt: Adaptable Composite Motion Modeling for Physics-Consistent Text-to-Video Generation
Haoran Qin, Renlong Wu, Tianyu Huang +3
While diffusion-based text-to-video (T2V) models have demonstrated impressive capability in generating realistic and temporally coherent videos, they often fail to respect fundamen…
Mitigating Error Accumulation in Co-Speech Motion Generation via Global Rotation Diffusion and Multi-Level Constraints
Xiangyue Zhang, Jianfang Li, Jianqiang Ren +1
Reliable long-horizon co-speech gesture generation requires precise motion representation and consistent structural priors across all joints. Existing generative methods typically…
SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis
Xiangyue Zhang, Jianfang Li, Jiaxu Zhang +4
Co-speech gesture generation must carefully integrate common rhythmic motion with rare yet essential semantic gestures. In this work, we propose SemTalk for holistic co-speech gest…
From Geometric Mimicry to Comprehensive Generation: A Context-Informed Multimodal Diffusion Model for Urban Morphology Synthesis
Fangshuo Zhou, Huaxia Li, Liuchang Xu +5
Urban morphology is fundamental to determining urban functionality and vitality. Prevailing simulation methods, however, often oversimplify morphological generation as a geometric…
IntrinsicAnything: Learning Diffusion Priors for Inverse Rendering Under Unknown Illumination
Xi Chen, Sida Peng, Dongchen Yang +4
This paper aims to recover object materials from posed images captured under an unknown static lighting condition. Recent methods solve this task by optimizing material parameters…
Transforming Visual Scene Graphs to Image Captions
Xu Yang, Jiawei Peng, Zihua Wang +7
We propose to Transform Scene Graphs (TSG) into more descriptive captions. In TSG, we apply multi-head attention (MHA) to design the Graph Neural Network (GNN) for embedding scene…
Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos
Yulin Pan, Xiangteng He, Biao Gong +4
Video temporal grounding aims to pinpoint a video segment that matches the query description. Despite the recent advance in short-form videos (\textit{e.g.}, in minutes), temporal…
Learning the Relation between Similarity Loss and Clustering Loss in Self-Supervised Learning
Jidong Ge, Yuxiang Liu, Jie Gui +5
Self-supervised learning enables networks to learn discriminative features from massive data itself. Most state-of-the-art methods maximize the similarity between two augmentations…
DARTSRepair: Core-failure-set Guided DARTS for Network Robustness to Common Corruptions
Xuhong Ren, Jianlang Chen, Felix Juefei-Xu +5
Network architecture search (NAS), in particular the differentiable architecture search (DARTS) method, has shown a great power to learn excellent model architectures on the specif…
MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation
Wenhao Li, Hong Liu, Hao Tang +2
Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting spat…
PANet: Perspective-Aware Network with Dynamic Receptive Fields and Self-Distilling Supervision for Crowd Counting
Xiaoshuang Chen, Yiru Zhao, Yu Qin +4
Crowd counting aims to learn the crowd density distributions and estimate the number of objects (e.g. persons) in images. The perspective effect, which significantly influences the…
Enhance Images as You Like with Unpaired Learning
Xiaopeng Sun, Muxingzi Li, Tianyu He +1
Low-light image enhancement exhibits an ill-posed nature, as a given image may have many enhanced versions, yet recent studies focus on building a deterministic mapping from input…
Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment
Yin Zhao, Minquan Wang, Longjun Cai
Eliminating the covariate shift cross domains is one of the common methods to deal with the issue of domain shift in visual unsupervised domain adaptation. However, current alignme…
End-to-End Dense Video Grounding via Parallel Regression
Fengyuan Shi, Weilin Huang, Limin Wang
Video grounding aims to localize the corresponding video moment in an untrimmed video given a language query. Existing methods often address this task in an indirect way, by castin…
Product-oriented Machine Translation with Cross-modal Cross-lingual Pre-training
Yuqing Song, Shizhe Chen, Qin Jin +3
Translating e-commercial product descriptions, a.k.a product-oriented machine translation (PMT), is essential to serve e-shoppers all over the world. However, due to the domain spe…
Support-Set Based Cross-Supervision for Video Grounding
Xinpeng Ding, Nannan Wang, Shiwei Zhang +5
Current approaches for video grounding propose kinds of complex architectures to capture the video-text relations, and have achieved impressive improvements. However, it is hard to…
Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters
Bowen Dong, Zitong Huang, Yuelin Guo +3
Weakly-supervised object detection (WSOD) has emerged as an inspiring recent topic to avoid expensive instance-level object annotations. However, the bounding boxes of most existin…
Mutually-aware Sub-Graphs Differentiable Architecture Search
Haoxian Tan, Sheng Guo, Yujie Zhong +2
Differentiable architecture search is prevalent in the field of NAS because of its simplicity and efficiency, where two paradigms, multi-path algorithms and single-path methods, ar…
JPGNet: Joint Predictive Filtering and Generative Network for Image Inpainting
Qing Guo, Xiaoguang Li, Felix Juefei-Xu +3
Image inpainting aims to restore the missing regions of corrupted images and make the recovery result identical to the originally complete image, which is different from the common…
Multi-Granularity Network with Modal Attention for Dense Affective Understanding
Baoming Yan, Lin Wang, Ke Gao +5
Video affective understanding, which aims to predict the evoked expressions by the video content, is desired for video creation and recommendation. In the recent EEV challenge, a d…
Salient Object Ranking with Position-Preserved Attention
Hao Fang, Daoxin Zhang, Yi Zhang +5
Instance segmentation can detect where the objects are in an image, but hard to understand the relationship between them. We pay attention to a typical relationship, relative salie…
E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning
Haiyang Xu, Ming Yan, Chenliang Li +4
Vision-language pre-training (VLP) on large-scale image-text pairs has achieved huge success for the cross-modal downstream tasks. The most existing pre-training methods mainly ado…
Effective Model Sparsification by Scheduled Grow-and-Prune Methods
Xiaolong Ma, Minghai Qin, Fei Sun +7
Deep neural networks (DNNs) are effective in solving many real-world problems. Larger DNN models usually exhibit better quality (e.g., accuracy) but their excessive computation res…
KVT: k-NN Attention for Boosting Vision Transformers
Pichao Wang, Xue Wang, Fan Wang +4
Convolutional Neural Networks (CNNs) have dominated computer vision for years, due to its ability in capturing locality and translation invariance. Recently, many vision transforme…