Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding
Read the original on arXiv Computer Vision →The paper introduces Parallel Tube Decoding (PTD), a generative approach for spatio‑temporal video grounding that splits the task into a temporal block and simultaneous time‑conditioned spatial blocks, eliminating token‑level and trajectory‑level dependencies. PTD uses Decoupled Block Attention to allow parallel spatial generation while maintaining shared video‑query context, and incorporates localization‑aware policy optimization for temporal boundaries and spatial geometry. Experiments on VidSTG show PTD cuts tube completion latency by 79× and boosts spatial decoding throughput by 92× compared to autoregressive decoding, while improving grounding accuracy and performing well on related tasks such as temporal grounding, VideoQA, and referring video object tracking.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.