FuguReport

Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding

Authors Hanoona Rasheed, Haania Siddiqui, Ming-Hsuan Yang, Fahad Shahbaz Khan, Salman Khan
Affiliations Apertix / University of California, Merced / Mohamed bin Zayed University of Artificial Intelligence
Categories Method / Video Grounding / Spatio-temporal grounding with decoding, Evaluation / Model Efficiency / Improved spatial decoding efficiency, Application / Multimodal Model / Trajectory prediction in video
License CC BY 4.0

Abstract Overview

This paper studies spatio-temporal video grounding (STVG) in multimodal large language models, targeting the inefficiency of autoregressively generating dense bounding-box trajectories across time. The authors propose Parallel Tube Decoding (PTD), which first predicts the temporal interval of the queried event and then decodes all time-conditioned spatial boxes simultaneously in parallel, reducing the sequential decoding depth to two rounds regardless of tube length. To support parallel box prediction without cross-box autoregressive interference, they introduce Decoupled Block Attention alongside localization-aware policy optimization using temporal and spatial rewards. Evaluations on VidSTG and HC-STVG show substantial improvements in both generation speed and grounding accuracy, with the learned localization transferring zero-shot to temporal grounding, grounded VideoQA, and referring video object tracking.

Novelty

The primary novelty is Parallel Tube Decoding, a generative STVG decoding paradigm that eliminates both token-level and trajectory-level autoregressive dependencies by decomposing generation into a temporal block followed by parallel time-conditioned spatial blocks. The method also introduces Decoupled Block Attention to isolate spatial box blocks from each other while maintaining shared multimodal context, supported by a localization-aware policy optimization objective.

Results

On VidSTG, PTD reduces Tube Completion Latency by 79× and raises spatial decoding throughput by 92× compared to standard unquantized autoregressive decoding while maintaining nearly constant latency as tube length scales. Built on a 4B backbone without external spatial decoders or tracking modules, the model achieves state-of-the-art or competitive grounding accuracy on VidSTG and HC-STVG. It also generalizes zero-shot to temporal grounding on Charades-STA and ActivityNet, grounded VideoQA on ReXTime, and video object tracking across Ref-DAVIS, Ref-YT-VOS, and ReasonVOS.

Key Points

  1. Parallel Tube Decoding reformulates STVG generation into temporal localization followed by parallel decoding of all spatial boxes, fixing the sequential decoding depth to two rounds independent of trajectory length.
  2. Decoupled Block Attention eliminates inter-box dependencies and prevents error propagation along the trajectory while preserving shared multimodal context for each temporal anchor.
  3. The 4B model substantially accelerates inference throughput and improves grounding accuracy over sequential baselines, demonstrating strong zero-shot transfer to temporal grounding, grounded VideoQA, and video object tracking.

References

This page was created using generative AI such as GPT-5, Claude Opus 4, Gemini 3, Gemini 3.1 Flash Image, and their higher-end successor versions. No guarantee can be made regarding its contents.