arXiv AI
Jun 19
Class-Incremental Motion Forecasting
arXiv:2603. 09420v3 Announce Type: replace-cross Abstract: Motion forecasting enables autonomous vehicles to anticipate scene evolution by predicting the future trajectories of dynamic agents.
SUMO: Segment and Track Any Motion with Nonlinear State Space Models
arXiv:2606. 29861v1 Announce Type: cross Abstract: Visual Object Tracking (VOT) and Moving Object Segmentation (MOS) are two fundamental tasks in computer vision that involve both spatial and temporal object dynamics.
Related stories
arXiv Machine Learning
Jul 3
COVTrack++: Learning Open-Vocabulary Multi-Object Tracking from Continuous Videos via a Synergistic Paradigm
arXiv:2603. 24016v2 Announce Type: replace-cross Abstract: Multi-Object Tracking (MOT) has traditionally focused on a few specific categories, restricting its applicability to real-world scenarios involving diverse objects.
arXiv AI
Aug 5
UniNav: A Unified World-Action Diffusion Model for Visual Navigation
arXiv:2608. 03244v1 Announce Type: new Abstract: Image-goal visual navigation is a fundamental capability for embodied agents.
Hugging Face Trending Papers
Aug 4
UniNav: A Unified World-Action Diffusion Model for Visual Navigation
Image-goal visual navigation is a fundamental capability for embodied agents. Existing navigation policies efficiently predict waypoint trajectories but lack visual foresight, while navigation world models can anticipate future observations but often require costly planning rollouts.
arXiv Computer Vision
Sep 17
StrucPhysVideo: Learning Physical Dynamics from Structured Captions and Robot Actions
arXiv:2609.18430v1 Announce Type: new Abstract: Modeling physical dynamics, including how objects move, interact, and change state, is central to video world models for embodied AI. We present StrucP...
arXiv Computer Vision
Aug 25
Competitive Memory Readout for Robust Video Object Segmentation: 2nd Place Technical Report for the MOSEv2 Track of the 8th LSVOS Challenge
arXiv:2608.22064v1 Announce Type: new Abstract: We present our solution for the MOSEv2 track of the 8th Large-scale Video Object Segmentation (LSVOS) Challenge at ECCV 2026. The challenge evaluates r...
arXiv Computer Vision
Aug 25
Motion-Aware Vision-Reference Alignment for Referring Multi-Object Tracking
arXiv:2511.17681v2 Announce Type: replace Abstract: Referring Multi-Object Tracking (RMOT) extends conventional multi-object tracking (MOT) by introducing natural language references for multi-modal...
arXiv Computer Vision
Aug 25
MotionDLO: Hybrid Event- and Frame-Based Tracking of Deformable Linear Objects
arXiv:2608.22398v1 Announce Type: cross Abstract: Reliably tracking moving deformable linear objects (DLOs) while simultaneously ensuring robustness, accuracy, and temporally consistent state estimat...
arXiv AI
Jun 17
GOT-JEPA: Generic Object Tracking with Model Adaptation and Occlusion Handling using Joint-Embedding Predictive Architecture
arXiv:2602. 14771v5 Announce Type: replace-cross Abstract: The human visual system tracks objects by integrating current observations with previously observed information, adapting to target and scene changes, and reasoning about occlusion at fine granularity.
arXiv AI
Jul 17
FoMoVLA: Bridging Visual Foresight and Motion Guidance for Vision-Language-Action Models
arXiv:2607. 14739v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have achieved impressive results in visuomotor policy learning, yet remain fundamentally reactive, mapping current observations and language to actions without explicit forward prediction of world dynamics.
arXiv Computer Vision
Oct 2
World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories
arXiv:2610.01742v1 Announce Type: cross Abstract: Equipping artificial agents with spatial intelligence requires a comprehensive generative prior over the dynamic 3D world. We propose World Motion Mo...
arXiv Computer Vision
Aug 25
GeoWAM: Visual Geometry World Action Models for Autonomous Driving
GeoWAM introduces a visual geometry world action model that predicts future scene geometry instead of future images, using point clouds to capture spatial structure and transformations. The model is pretrained to forecast geometry, then a geometry-conditioned action head predicts ego trajectories. Experiments show that this geometry-based approach yields stronger driving policies than image-based alternatives.