1 citations · 1 across the 14 of their papers we have counts for
15 papers
ReMem: Streaming Video Understanding With Long Context Retention
Li Yiheng, He Xu, Wang Shaobo +2
Despite their impressive performance on a wide range of video understanding tasks, current Vision Language Models (VLMs) are predominantly designed for offline scenarios and strugg…
EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal
Feier Wu, Wanke Xia, Xu He +8
Video object removal must eliminate not only the target object but also its induced effects while maintaining high-fidelity and spatiotemporally coherent restoration. Existing meth…
MindFlow: Harmonizing Cognitive Semantics and Acoustic Dynamics for Facial Animation Generation in Dyadic Conversations
Hejia Chen, Haoxian Zhang, Xu He +4
Generating lifelike facial animation for dyadic conversations requires reconciling high-level cognitive intent with precise low-level motor reflexes, yet existing methods fall shor…
UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating
Jiehui Huang, Yuechen Zhang, Bin Xia +7
Generating a coherent multi-shot video requires structured cross-shot memory. Subject appearance, scene context, and speaker identity must persist across cuts. Existing approaches…
Semantic-Aware Prefix Learning for Token-Efficient Image Generation
Qingfeng Li, Haoxian Zhang, Xu He +4
Visual tokenizers play a central role in latent image generation by bridging high-dimensional images and tractable generative modeling. However, most existing tokenizers are still…
3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation
Zhixue Fang, Xu He, Songlin Tang +5
Existing methods for human motion control in video generation typically rely on either 2D poses or explicit 3D parametric models (e.g., SMPL) as control signals. However, 2D poses…
UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation
Jiehui Huang, Yuechen Zhang, Xu He +7
Recent video generation models demonstrate impressive synthesis capabilities but remain limited by single-modality conditioning, constraining their holistic world understanding. Th…
From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping
Xu He, Haoxian Zhang, Hejia Chen +7
Audio-driven visual dubbing aims to synchronize a video's lip movements with new speech but is fundamentally challenged by the lack of ideal training data: paired videos differing…
UniPart: Part-Level 3D Generation with Unified 3D Geom-Seg Latents
Xufan He, Yushuang Wu, Xiaoyang Guo +5
Part-level 3D generation is essential for applications requiring decomposable and structured 3D synthesis. However, existing methods either rely on implicit part segmentation with…
VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstruction
Shaobo Wang, Tianle Niu, Runkang Yang +6
The scalability of video understanding models is increasingly limited by the prohibitive storage and computational costs of large-scale video datasets. While data synthesis has imp…
StableDub: Taming Diffusion Prior for Generalized and Efficient Visual Dubbing
Liyang Chen, Tianze Zhou, Xu He +7
The visual dubbing task aims to generate mouth movements synchronized with the driving audio, which has seen significant progress in recent years. However, two critical deficiencie…
HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning
Liyang Chen, Tianxiang Ma, Jiawei Liu +7
Human-Centric Video Generation (HCVG) methods seek to synthesize human videos from multimodal inputs, including text, image, and audio. Existing methods struggle to effectively coo…
MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement
Xu He, Xiaoyu Li, Di Kang +7
Existing works in single-image human reconstruction suffer from weak generalizability due to insufficient training data or 3D inconsistencies for a lack of comprehensive multi-view…
Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model
Xu He, Qiaochu Huang, Zhensong Zhang +7
Co-speech gestures, if presented in the lively form of videos, can achieve superior visual effects in human-machine interaction. While previous works mostly generate structural hum…
Enhancing Expressiveness in Dance Generation via Integrating Frequency and Music Style Information
Qiaochu Huang, Xu He, Boshi Tang +6
Dance generation, as a branch of human motion generation, has attracted increasing attention. Recently, a few works attempt to enhance dance expressiveness, which includes genre ma…