InstAP introduces instance-aware pre-training with a new dual-granularity dataset InstVL that improves both fine-grained instance retrieval and global video understanding over standard VLP baselines.
hub
Sam 2: Segment anything in images and videos
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
representative citing papers
IBISAgent enables MLLMs to perform iterative pixel-level visual reasoning for biomedical object referring and segmentation via text-based clicks and agentic RL, outperforming prior SOTA methods without model modifications.
MICo-150K is a new 150K-image dataset with 7 tasks, a De&Re real-image subset, MICo-Bench, and Weighted-Ref-VIEScore metric that improves AI models for generating consistent composites from arbitrary numbers of reference images.
Hoi! is a new multimodal dataset of force-grounded articulated object manipulations with cross-view video and tactile sensing from human hands and robotic grippers.
RiGS decomposes scenes into static, rigid, and transient 4D Gaussians with an object-wise dynamic mask and scene flow guidance to model multi-scale motions and achieve SOTA novel view synthesis.
V2-SAM adapts SAM2 to cross-view object correspondence with geometry-aware and appearance-based prompt generators plus a post-hoc cyclic consistency selector, reporting new state-of-the-art results on Ego-Exo4D, DAVIS-2017, and HANDAL-X.
A new dataset with high-fidelity close-up garment images and full/close-up try-on videos plus the VGID metric enables better texture and structure preservation in high-resolution video virtual try-on.
TinySAM 2 reaches 90% of SAM 2.1 performance on DAVIS and SA-V using 7% of the memory tokens and 3% of the training data via frame selection, spatial average pooling, temporal similarity-based token pruning, and a RepViT image encoder.
Extends online 2D multi-camera tracking to 3D via depth-based point cloud reconstruction, clustering for 3D boxes, and local ID consistency for global data association, placing 3rd on 2025 AI City Challenge 3D MTMC dataset.
VVitCutLER introduces VitCut as a temporally stable pseudo-label generator with cross-frame consistency and feature aggregation to improve unsupervised video object detection and segmentation.
citing papers explorer
-
InstAP: Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding
InstAP introduces instance-aware pre-training with a new dual-granularity dataset InstVL that improves both fine-grained instance retrieval and global video understanding over standard VLP baselines.
-
IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentation
IBISAgent enables MLLMs to perform iterative pixel-level visual reasoning for biomedical object referring and segmentation via text-based clicks and agentic RL, outperforming prior SOTA methods without model modifications.
-
MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition
MICo-150K is a new 150K-image dataset with 7 tasks, a De&Re real-image subset, MICo-Bench, and Weighted-Ref-VIEScore metric that improves AI models for generating consistent composites from arbitrary numbers of reference images.
-
Hoi! - A Multimodal Dataset for Force-Grounded, Cross-View Articulated Manipulation
Hoi! is a new multimodal dataset of force-grounded articulated object manipulations with cross-view video and tactile sensing from human hands and robotic grippers.
-
RiGS: Rigid-aware 4D Gaussian Splatting from a Single Monocular Video
RiGS decomposes scenes into static, rigid, and transient 4D Gaussians with an object-wise dynamic mask and scene flow guidance to model multi-scale motions and achieve SOTA novel view synthesis.
-
V$^{2}$-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence
V2-SAM adapts SAM2 to cross-view object correspondence with geometry-aware and appearance-based prompt generators plus a post-hoc cyclic consistency selector, reporting new state-of-the-art results on Ego-Exo4D, DAVIS-2017, and HANDAL-X.
-
Eevee: Towards Close-up High-resolution Video-based Virtual Try-on
A new dataset with high-fidelity close-up garment images and full/close-up try-on videos plus the VGID metric enables better texture and structure preservation in high-resolution video virtual try-on.
-
TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model
TinySAM 2 reaches 90% of SAM 2.1 performance on DAVIS and SA-V using 7% of the memory tokens and 3% of the training data via frame selection, spatial average pooling, temporal similarity-based token pruning, and a RepViT image encoder.
-
Online 3D Multi-Camera Perception through Robust 2D Tracking and Depth-based Late Aggregation
Extends online 2D multi-camera tracking to 3D via depth-based point cloud reconstruction, clustering for 3D boxes, and local ID consistency for global data association, placing 3rd on 2025 AI City Challenge 3D MTMC dataset.
-
VVitCutLER: Towards Unsupervised Object Detection and Segmentation in Videos
VVitCutLER introduces VitCut as a temporally stable pseudo-label generator with cross-frame consistency and feature aggregation to improve unsupervised video object detection and segmentation.