Fine-grained understanding of operating room (OR) activity could enable workflow-aware assistance, yet remains difficult due to clutter, occlusions, and limited sensing. The prevailing approach to model this environment is scene graphs as an interpretable representation of OR interactions.
arXiv:2603. 09731v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) are increasingly considered as a foundation for embodied agents, yet it remains unclear whether they can reliably reason about the long-term physical consequences of actions from an egocentric viewpoint.
The paper introduces STITCH, a training‑free method that partitions videos into semantically meaningful temporal chunks using a frozen video‑text backbone. By detecting changes in the embedding sequence of short video windows, STITCH produces reusable temporal abstractions that can be applied to multiple tasks such as event boundary detection, language‑based moment retrieval, and frame selection for vision‑language models. Experiments show that STITCH performs competitively with specialized methods while requiring no task‑specific training, especially when processing is limited to a few frames or tokens.
Hand-object interaction (HOI) recognition requires capturing both hand manipulations and object transformations. However, existing video-language models often fall into shortcuts by relying on spurious correlations among hands, objects, or environmental context, rather than reasoning from the appearance and dynamics of hands and objects themselves.
arXiv:2608. 10932v1 Announce Type: cross Abstract: Understanding camera motion is fundamental to video perception, with applications in spatial intelligence and controllable video generation.
arXiv:2604. 27975v2 Announce Type: replace-cross Abstract: Traditional Shot Boundary Detection (SBD) inherently struggles with complex transitions by formulating the task around isolated cut points, frequently yielding corrupted video shots.
arXiv:2607. 23077v1 Announce Type: new Abstract: Modeling multi-entity temporal data requires capturing dependencies across entities, time, and their interactions.
arXiv:2608.30584v1 Announce Type: new Abstract: Despite the impressive progress of recent MLLMs on spatio-temporal video grounding (STVG), existing evaluations and training data focus primarily on si...
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.
ConsensusTAS is a self‑supervised, label‑free method for temporal action segmentation in long construction videos. It segments continuous video streams into distinct activity phases by leveraging internal consensus among candidate segmentations, and it has been evaluated on three public datasets, outperforming state‑of‑the‑art methods. In real‑world construction footage, the model successfully identified fine‑grained actions within bricklaying, and it can run on a CPU, making it suitable for mobile robotic platforms.
arXiv:2606. 06853v1 Announce Type: cross Abstract: The new era has witnessed a remarkable capability to extend Vision-Language Models (VLMs) for tackling tasks of video understanding.
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.