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

Source: https://huggingface.co/papers/2608.28192

Abstract

Parallel Tube Decoding enables simultaneous spatial and temporal video grounding by removing autoregressive dependencies, drastically cutting latency while improving accuracy.

Spatio-temporal video grounding(STVG) requires models to identify when a referred event occurs and localize the target entity throughout that interval. Existing multimodal large language models typically serialize dense localization trajectories autoregressively, causing decoding latency to grow with tube length and allowing localization errors to propagate across time. We introduceParallel Tube Decoding(PTD), a generative formulation that decomposes grounding into a temporal block followed by time-conditioned spatial blocks decoded simultaneously. This removes both token-level and trajectory-level dependencies, reducing the sequential decoding depth to a fixed 1 + 1 rounds, independent of tube length. To enable parallel spatial generation, we introduceDecoupled Block Attention, which preserves access to shared video-query context while eliminating cross-box dependencies, together withlocalization-aware policy optimizationfor temporal boundaries and spatial geometry. On VidSTG, PTD reducesTube Completion Latencyby 79x and increases spatial decoding throughput by 92x over standardautoregressive decoding, while also improving grounding accuracy. With a compact 4B backbone, our model performs favorably well on VidSTG and HC-STVG, and generalizes zero-shot to temporal grounding, grounded VideoQA, and referring video object tracking. Our results show parallel tube generation is an efficient and effective alternative to autoregressive localization in videos.

View arXiv pageView PDFProject pageGitHub18Add to collection

Get this paper in your agent:

hf papers read 2608\.28192

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.28192 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.28192 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.28192 in a Space README.md to link it from this page.

Collections including this paper1