4 papers · 1 filter
OPERA: A Unified Omnimodal Progressive Spatio-Temporal Reasoning Agent for Referring Video Segmentation
Jingchen Ni, Yuji Wang, Shannan Yan +3
Referring video segmentation with heterogeneous multimodal queries---spanning text, audio, and reference images---demands both robust cross-modal understanding and precise spatio-t…
MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization
Jingchen Ni, Cangjin Yu, Dan Jiang +6
Driven by Artificial Intelligence-Generated Content (AIGC), the authenticity of audio-visual content is facing severe challenges. Temporal Forgery Localization (TFL) aims to precis…
Learning Cross-View Object Correspondence via Cycle-Consistent Mask Prediction
Shannan Yan, Leqi Zheng, Keyu Lv +7
We study the task of establishing object-level visual correspondence across different viewpoints in videos, focusing on the challenging egocentric-to-exocentric and exocentric-to-e…
ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices
Hao Yu, Tangyu Jiang, Shuning Jia +7
The Transformer architecture has revolutionized various regions since it was proposed, and its effectiveness largely depends on the ability to encode positional information. Tradit…