arXiv:2607. 21267v1 Announce Type: new Abstract: Comprehensive basketball video understanding requires resolving not only what event occurs, but also who is responsible and when the key evidence appears.
arXiv:2606. 09181v1 Announce Type: cross Abstract: Recent advances in video multimodal models have significantly improved VideoQA performance.
arXiv:2606. 07433v1 Announce Type: cross Abstract: Video understanding is being rapidly transformed by multimodal large language models (MLLMs), as research moves from short clips to long, multimodal, and knowledge-intensive video scenarios.
Multimodal Large Language Models (MLLMs) have achieved strong progress in video understanding, yet it remains challenging because the token limitation makes MLLMs difficult to capture temporally sparse evidence. Existing methods typically rely on uniform sampling, or frame selection, but these strategies usually optimize either broad temporal coverage or local relevance, making it difficult to preserve both global storyline context and fine-grained evidence.
arXiv:2602. 12080v2 Announce Type: replace Abstract: Despite recent advances in AI, event data collection in soccer still relies heavily on labor-intensive manual annotation.
Precise Event Spotting (PES) requires distinguishing visually similar yet semantically distinct adjacent frames, making it fundamentally different from image classification and coarse action recognition. Although self-distillation methods such as DINO have shown strong representation learning ability in images, we find that directly applying them to PES is ineffective: without supervised guidance, subtle but crucial motion cues are often suppressed as noise, leading to representations that are insensitive to precise event boundaries.
arXiv:2606. 09327v1 Announce Type: cross Abstract: Football event data constitute a rich spatiotemporal source for quantitative analysis of player actions in team sports.
arXiv:2606. 12047v1 Announce Type: cross Abstract: In this paper, we address the problem of zero-shot understanding of accidents from surveillance videos by identifying when an impact event occurs, what type of impact it is, and where in the frame it occurs using natural language.
arXiv:2607. 04872v1 Announce Type: cross Abstract: Reasoning temporal localization (RTL) requires a model to generate an answer that itself contains the time interval supporting it, so high-level reasoning and precise temporal grounding must be produced jointly in a single response.
WALL-WM is a World Action Model that shifts video-action learning from chunk-centric optimization to event-grounded Vision-Language-Action pretraining, using semantically coherent action events as the atomic unit of learning. Existing WAMs commonly initialize from multimodal or video foundation models and then optimize fixed-length action chunks conditioned directly on the current observation and instruction.
arXiv:2607. 08763v1 Announce Type: cross Abstract: Reasoning has become a core capability for large models, especially when reliable decisions require understanding logical consequences.
arXiv:2605. 21917v2 Announce Type: replace-cross Abstract: Training Vision Language Models (VLMs) for video event reasoning requires high-quality structured annotations capturing not only what happened, but when, where, why, and with what consequence, at a scale manual labelling cannot support.
In this paper, we address the problem of zero-shot understanding of accidents from surveillance videos by identifying when an impact event occurs, what type of impact it is, and where in the frame it occurs using natural language. We propose a three-stage pipeline that decomposes the accident understanding into when, what, and where.