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.
arXiv:2607. 13421v1 Announce Type: cross Abstract: Spatio-Temporal Video Grounding (STVG) aims to retrieve the visual trajectory of a specific object from a video stream as described by a natural language expression.
arXiv:2607. 24570v1 Announce Type: cross Abstract: Large-scale video platforms process millions of uploads hourly, requiring moderation systems that can localize when and where policy violations occur within each video.
arXiv:2606.06158v2 Announce Type: replace Abstract: Adaptive video tokenisation seeks to dynamically allocate token budgets based on the underlying visual complexity of a sequence. Current continuous...
arXiv:2608.20473v1 Announce Type: new Abstract: Video language models process videos as dense visual-token sequences with substantial representational redundancy. Compressing these sequences is there...
arXiv:2608.21030v1 Announce Type: cross Abstract: Video multimodal large language models have advanced significantly, yet fine-grained motion-temporal understanding remains fragile. The core bottlene...
arXiv:2607. 02963v1 Announce Type: cross Abstract: Dense video captioning aims to generate temporally grounded descriptions of video events, benefiting both event-level video understanding and generation.
arXiv:2609.02359v1 Announce Type: new Abstract: Visual grounding maps language referents to spatial targets and is central to open-vocabulary perception with vision-language models. Existing methods...
arXiv:2609.02204v1 Announce Type: new Abstract: Text-Video Retrieval (TVR) retrieves videos that match a natural-language query, but extending image-text models such as CLIP to videos is fundamentall...
arXiv:2606. 29023v1 Announce Type: cross Abstract: Spatio-temporal grounding in long videos requires precise temporal localization and robust object tracking conditioned on natural-language queries.
Text-Video Retrieval (TVR) retrieves videos that match a natural-language query, but extending image-text models such as CLIP to videos is fundamentally limited by the lack of temporal modeling. Video...
arXiv:2607. 15778v1 Announce Type: cross Abstract: Video Large Language Models (Video LLMs) have made significant advancements in various video understanding tasks.
In video understanding, vision-language models (VLMs) must ingest massive numbers of visual tokens, causing the computational and memory cost of the prefill stage to rise sharply. Such visual sequences are highly redundant along the spatio-temporal dimension, yet a high compression ratio is often accompanied by the loss of critical details.