12 papers
Fovea-JEPA: Overcoming Geometric Blind Spots in V-JEPA for Camera Motion Recognition
Xiangkun Shi, Hanhui Li, Shiyue Zhang +4
Camera motion recognition requires separating viewpoint changes caused by camera translation, rotation, or zoom from object motion and scene dynamics. Video-language models often r…
SAM2Matting: Generalized Image and Video Matting
Ruiqi Shen, Guangquan Jie, Chang Liu +1
Despite impressive advances in image matting, video matting remains challenging due to the inherent gap between high-level tracking, which requires frame-wise understanding, and lo…
Inclusive Interactive Collisions for Multi-View Consistent Compositional 3D Generation
Chang Liu, Mingwen Shao, Xiang Lv +5
Recent breakthroughs in 3D generation have advanced notably with the development of text-to-image diffusion model. However, existing methods remain two practical challenges: (1) Th…
Masked Next-Scale Prediction for Self-supervised Scene Text Recognition
Zhuohao Chen, Zeng Li, Yifei Zhang +2
Scene Text Recognition requires modeling visual structures that evolve from coarse layouts to fine-grained character strokes. Training such models relies on large amounts of annota…
Count Anything at Any Granularity
Chang Liu, Haoning Wu, Weidi Xie
Open-world object counting remains brittle: despite rapid advances in vision-language models (VLMs), reliably counting the objects a user intends is far from solved. We argue that…
Improving Human Image Animation via Semantic Representation Alignment
Chang Liu, Mengting Chen, Yixuan Huang +5
The field of image-to-video generation has made remarkable progress. However, challenges such as human limb twisting and facial distortion persist, especially when generating long…
Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE
Yangming Shi, Shixiang Zhu, Tao Shen +14
We present Mamoda2.5, a unified AR-Diffusion framework that seamlessly integrates multimodal understanding and generation within a single architecture. To efficiently enhance the m…
ViewSAM: Learning View-aware Cross-modal Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking
Jiawei Ge, Xintian Zhang, Jiuxin Cao +9
Cross-view Referring Multi-Object Tracking (CRMOT) aims to track multiple objects specified by natural language across multiple camera views, with globally consistent identities. D…
Video Generation with Predictive Latents
Yian Zhao, Feng Wang, Qiushan Guo +4
Video Variational Autoencoder (VAE) enables latent video generative modeling by mapping the visual world into compact spatiotemporal latent spaces, improving training efficiency an…
BOOKAGENT: Orchestrating Safety-Aware Visual Narratives via Multi-Agent Cognitive Calibration
Bo Gao, Chang Liu, Yuyang Miao +2
Recent advancements in Large Generative Models (LGMs) have revolutionized multi-modal generation. However, generating illustrated storybooks remains an open challenge, where prior…
MammothModa2: A Unified AR-Diffusion Framework for Multimodal Understanding and Generation
Tao Shen, Xin Wan, Taicai Chen +10
Unified multimodal models aim to integrate understanding and generation within a single framework, yet bridging the gap between discrete semantic reasoning and high-fidelity visual…
TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning
Junwen Pan, Qizhe Zhang, Rui Zhang +5
Temporal search aims to identify a minimal set of relevant frames from tens of thousands based on a given query, serving as a foundation for accurate long-form video understanding.…