6 papers · 1 filter
NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation
Yujiang Pu, Yu Kong
Diffusion models have recently advanced text-to-video (T2V) generation, yet they still struggle with fine-grained compositional alignment, such as attribute binding, spatial relati…
Spatially Prompted Visual Trajectory Prediction for Egocentric Manipulation
Yifan Li, Xinyu Zhou, Yunhao Ge +2
Language instructions offer a flexible way to specify task semantics but can become ambiguous in cluttered scenes containing multiple visually similar objects and candidate targets…
ProcObject-10K: Benchmarking Object-Centric Procedural Understanding in Instructional Videos
Wenliang Guo, Yu Kong
Procedural activities are fundamentally driven by object state transitions, yet existing instructional video benchmarks remain action-centric and cannot evaluate whether models rea…
Procedural Mistake Detection via Action Effect Modeling
Wenliang Guo, Yujiang Pu, Yu Kong
Mistake detection in procedural tasks is essential for building intelligent systems that support learning and task execution. Existing approaches primarily analyze how an action is…
SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding
Zixu Cheng, Yujiang Pu, Shaogang Gong +2
Temporal grounding, also known as video moment retrieval, aims at locating video segments corresponding to a given query sentence. The compositional nature of natural language enab…
ATM: Action Temporality Modeling for Video Question Answering
Junwen Chen, Jie Zhu, Yu Kong
Despite significant progress in video question answering (VideoQA), existing methods fall short of questions that require causal/temporal reasoning across frames. This can be attri…