arXiv AI
Aug 6
Robust and Efficient Motion Reasoning for Privacy-Aware Classroom Incident Recognition
arXiv:2608. 05115v1 Announce Type: cross Abstract: Can computer vision help make classrooms safer?
Robust and Efficient Motion Reasoning for Privacy-Aware Classroom Incident Recognition
Can computer vision help make classrooms safer? In this pilot study, we investigate privacy-aware and computationally efficient classroom incident recognition from CCTV-style observations.
Related stories
arXiv AI
Jun 29
Can LLMs Reason About Attention? Towards Zero-Shot Analysis of Multimodal Classroom Behavior
arXiv:2604. 03401v4 Announce Type: replace-cross Abstract: Understanding student engagement usually requires time-consuming manual observation or invasive recording that raises privacy concerns.
arXiv Computer Vision
6d ago
Thinking with Cameras: Active Visual Reasoning via Dynamic Viewpoint Control for Surveillance Video Understanding
The paper introduces CamVLM, a framework that equips large vision‑language models with the ability to actively control camera viewpoints for improved surveillance video understanding. It presents two new datasets: CCTV‑Anomaly, a large‑scale surveillance video collection with detailed captions and event annotations, and CamTrack‑53K, an object‑centric viewpoint trajectory dataset for learning camera actions. Using reinforcement learning, CamVLM learns long‑horizon observation strategies, achieving state‑of‑the‑art performance in both passive and dynamic viewpoint settings.
arXiv Computer Vision
Sep 7
MINT: A Unified Model for World-Space Camera and Hand Motion Estimation from Scalable Egocentric Pipeline Supervision
MINT is a foundation model that directly predicts world-space two-hand trajectories from egocentric RGB video, jointly estimating camera motion, hand states, and hand presence in a single spatiotemporal representation. It uses an open-source labeling pipeline, EGOPIPELINE, to generate large-scale pseudo-labels for pretraining, followed by fine-tuning on a small set of high-quality joint annotations. The model outperforms existing multi-stage approaches in accuracy and speed, and generalizes zero‑shot to unseen egocentric datasets.
arXiv Computer Vision
Sep 10
Bounding-Box Trajectories Matter for Video Anomaly Detection
arXiv:2605.21957v2 Announce Type: replace Abstract: Video anomaly detection is critical for public safety and security, yet remains highly challenging despite extensive research due to large variatio...
arXiv Computer Vision
Sep 24
Track2Art: Motion-Centric Articulated Object Model Recovery from 2D Point Trackers
Track2Art is a motion‑centric framework that recovers articulated object models from RGB‑D interaction videos by lifting 2D point tracks into 3D trajectories. It groups these trajectories into rigid‑part hypotheses and uses learned‑analytic reasoning to infer directed kinematic relations, joint types, and joint geometry. On the PartNet‑Mobility benchmark, it achieves 0.695 Point IoU and 0.410 end‑to‑end J@20 without requiring ground‑truth part counts or test‑time optimization.
arXiv AI
Jun 29
EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning
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.
arXiv Computer Vision
Sep 17
Category Level 6D Object Pose Estimation from a Single RGB Image using Diffusion
The paper presents a generative framework that estimates category-level 6D pose and 3D size of objects from a single RGB image, using score-based diffusion models to produce a multi-hypothesis pose distribution. It replaces costly likelihood pruning with a Mean Shift approach to isolate the mode as the final pose estimate, achieving state-of-the-art results on the REAL275 benchmark. The method also decouples detection from pose estimation, enabling robust zero-shot generalisation on the Wild6D dataset and extending naturally to video sequences by propagating the pose distribution over time.
arXiv Computation and Language
Aug 25
SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening
arXiv:2605.17610v2 Announce Type: replace-cross Abstract: The rapid growth of online video platforms and AI-generated content has made reliable video guardrails a key challenge for safety and real-wo...
arXiv AI
4d ago
WeLike2Party! In-Context Motion Transfer for Multi-Human Image Animation
arXiv:2609.36937v1 Announce Type: cross Abstract: Human image animation aims to transfer motion from a driving video to subjects in a reference image. Despite remarkable progress in video generation,...
arXiv AI
Aug 12
Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation
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 Computer Vision
Sep 7
Object Concepts Emerge from Motion
The paper introduces a biologically inspired framework that learns object‑centric visual representations from raw videos without human annotations or camera calibration. By using motion boundaries detected via optical flow and clustering to create pseudo‑instance masks, the method supervises a single‑image encoder with pixel‑level pairwise metric learning. Training on 195 million pseudo‑labeled frames and expanding to 421 million frames through Motion‑Verified Self‑Training, the approach yields Swin‑based encoders that outperform or match supervised and self‑supervised baselines on tasks such as monocular depth estimation, 3D object detection, 3D occupancy prediction, and end‑to‑end planning.