REVIEW 17 cited by
Track Anything: Segment Anything Meets Videos
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Track Anything: Segment Anything Meets Videos
read the original abstract
Recently, the Segment Anything Model (SAM) gains lots of attention rapidly due to its impressive segmentation performance on images. Regarding its strong ability on image segmentation and high interactivity with different prompts, we found that it performs poorly on consistent segmentation in videos. Therefore, in this report, we propose Track Anything Model (TAM), which achieves high-performance interactive tracking and segmentation in videos. To be detailed, given a video sequence, only with very little human participation, i.e., several clicks, people can track anything they are interested in, and get satisfactory results in one-pass inference. Without additional training, such an interactive design performs impressively on video object tracking and segmentation. All resources are available on {https://github.com/gaomingqi/Track-Anything}. We hope this work can facilitate related research.
Forward citations
Cited by 17 Pith papers
-
ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models
ViSRA boosts MLLM 3D spatial reasoning performance by up to 28.9% on unseen tasks via a plug-and-play video-based agent that extracts explicit spatial cues from expert models without any post-training.
-
TOC-Bench: A Temporal Object Consistency Benchmark for Video Large Language Models
TOC-Bench is an object-track-grounded benchmark that filters for temporally dependent questions and shows Video-LLMs have major weaknesses in event counting, ordering, identity reasoning, and hallucination detection.
-
TOC-Bench: A Temporal Object Consistency Benchmark for Video Large Language Models
TOC-Bench is a new diagnostic benchmark that reveals major weaknesses in temporal object consistency for Video-LLMs, including event counting, ordering, identity reasoning, and hallucination avoidance.
-
Space-Time Forecasting of Dynamic Scenes with Motion-aware Gaussian Grouping
MoGaF groups Gaussians by motion in 4D splatting representations to enable stable long-term forecasting of dynamic scenes.
-
LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents
LangDriveCTRL decomposes driving videos into 3D scene graphs and uses an agentic pipeline with specialized multi-modal agents to perform language-controlled object and behavior edits, achieving nearly 2x higher instru...
-
One Identity, Many Roles: Multimodal Entity Coreference for Enhanced Video Situation Recognition
CineMEC performs multimodal entity coreference by clustering visual entities and aligning them with text role mentions to boost captioning and grounding performance on an extended VidSitu dataset.
-
DP-DeGauss: Dynamic Probabilistic Gaussian Decomposition for Egocentric 4D Scene Reconstruction
DP-DeGauss uses probabilistic Gaussian decomposition with dynamic routing and category masks to achieve the first explicit disentanglement of background, hand, and object components in egocentric 4D scene reconstructi...
-
Learning to Synergize Semantic and Geometric Priors for Limited-Data Wheat Disease Segmentation
SGPer combines DINOv2 semantic priors converted to dense prompts with SAM geometric priors through disease-sensitive adapters and dynamic consistency filtering to deliver robust limited-data wheat disease segmentation.
-
SatSAM2: Motion-Constrained Video Object Tracking in Satellite Imagery using Promptable SAM2 and Kalman Priors
SatSAM2 improves satellite video object tracking by integrating Kalman motion priors and a motion state machine into SAM2, outperforming prior methods with a 5.84% AUC gain on OOTB while introducing the MVOT synthetic...
-
One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory
TrajViT tokenizes videos via panoptic sub-object trajectories, achieving 10x token reduction and outperforming ViT3D by 6% on retrieval and 5.2% on VideoQA tasks with faster training and inference.
-
RoDyGS: Robust Dynamic Gaussian Splatting for Casual Videos
RoDyGS separates static and dynamic elements in monocular videos using Gaussian splatting with regularization and introduces the Kubric-MRig benchmark for pose-free dynamic novel view synthesis.
-
VFM-SDM: A vision foundation model-based framework for training-free, marker-free, and calibration-free structural displacement measurement
VFM-SDM enables accurate multi-directional structural displacement measurement from video using pre-trained vision models for camera estimation and point tracking, combined with geometry constraints, without task-spec...
-
Do Instance Priors Help Weakly Supervised Semantic Segmentation?
SeSAM adapts SAM for weakly supervised semantic segmentation via mask decomposition, skeleton-based point sampling, coverage-based mask selection, and pseudo-label iteration, outperforming baselines while cutting anno...
-
ET-SAM: Efficient Point Prompt Prediction in SAM for Unified Scene Text Detection and Layout Analysis
A lightweight point decoder plus task-prompt joint training yields ~3× faster SAM-based hierarchical text detection with competitive HierText results and +11% average F-score on three single-level benchmarks.
-
Reinforcement Learning for Unsupervised Domain Adaptation in Spatio-Temporal Echocardiography Segmentation
RL4Seg3D applies reinforcement learning with novel reward functions and fusion to adapt echocardiography segmentation models across domains, improving accuracy, anatomical validity, and temporal consistency on over 30...
-
On Efficient Variants of Segment Anything Model: A Survey
A survey that reviews efficient variants of the Segment Anything Model, categorizes acceleration strategies, and provides a unified hardware evaluation on benchmarks.
-
Faster Segment Anything: Towards Lightweight SAM for Mobile Applications
MobileSAM is a 60x smaller distilled version of SAM that matches original performance and runs 5x faster than concurrent FastSAM while supporting CPU inference.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.