CUTAL scores multi-frame clips for uncertainty and enforces temporal diversity to train transformer MOT models to near full-supervision performance with 50% of the labels.
hub Canonical reference
MOT16: a benchmark for multi-object tracking.arXiv preprint arXiv:1603.00831
Canonical reference. 80% of citing Pith papers cite this work as background.
15
Pith papers citing it
Background
80% of classified citations
abstract
Standardized benchmarks are crucial for the majority of computer vision applications. Although leaderboards and ranking tables should not be over-claimed, benchmarks often provide the most objective measure of performance and are therefore important guides for reseach. Recently, a new benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal of collecting existing and new data and creating a framework for the standardized evaluation of multiple object tracking methods. The first release of the benchmark focuses on multiple people tracking, since pedestrians are by far the most studied object in the tracking community. This paper accompanies a new release of the MOTChallenge benchmark. Unlike the initial release, all videos of MOT16 have been carefully annotated following a consistent protocol. Moreover, it not only offers a significant increase in the number of labeled boxes, but also provides multiple object classes beside pedestrians and the level of visibility for every single object of interest.
hub tools
citation-role summary
background 4
method 1
citation-polarity summary
verdicts
UNVERDICTED 15representative citing papers
CityOS is an edge runtime that enforces a three-tier privacy API for urban sensors: local raw data, differentially private single-location stats, and cross-location aggregates with per-user budgets enforced on devices.
A learnable nonlocal block that mimics classical neighbor matching and collaborative filtering on multiscale features produces competitive RAW denoising with far fewer parameters than current deep models and generalizes across sensors.
Introduces the U-HOI task and shows MLLMs plus a language-to-graph pipeline can handle human-object interactions without any predefined vocabulary at training or inference time.
STORM is an end-to-end MLLM for referring multi-object tracking that uses task-composition learning to leverage sub-task data and introduces the STORM-Bench dataset, achieving SOTA results.
OmniTrack++ improves omnidirectional multi-object tracking with trajectory feedback through DynamicSSM stabilization, FlexiTrack instances, ExpertTrack Memory with Mixture-of-Experts, and adaptive Tracklet Management, achieving SOTA HOTA gains on JRDB and new EmboTrack benchmark.
A graph neural network framework learns affinities from appearance and motion then solves bipartite matching for online multiple-object tracking.
ERPPO adds a DSA-based ambiguity estimator to MAPPO and switches between L1 and L2 entropy regularization to improve exploration and stability in non-stationary multi-dimensional observations.
The paper derives an occlusion-aware multi-object tracking method that assigns each object an expected detection probability over the reduced Palm density within a multi-Bernoulli mixture filter.
SAMOFT improves multi-object tracking by using SAM segmentation and optical flow for pixel-level motion matching, flexible centroid correction, and training-free motion pattern fixes on top of standard Kalman and ReID baselines.
TCMP achieves SOTA MOT metrics (HOTA 63.4%, IDF1 65.0%, AssA 49.1%) with 0.014x parameters and 0.05x FLOPs of the previous best method by using a simple dilated TCN regressor.
Distilled SAM 3 and DINOv3 models deliver near-teacher accuracy in pig tracking (92.29% MOTA, 96.15% IDF1) and behavior classification while achieving 7.77x parameter reduction and fitting on Jetson Orin NX with headroom.
HyperSSM integrates hypergraphs and state space models to let correlated objects mutually refine motion estimates, stabilizing trajectories under noise and occlusion for state-of-the-art multi-object tracking.
A survey that taxonomizes non-Transformer vision models and evaluates their practical trade-offs across efficiency, scalability, and robustness.
A YOLOv11-based desktop application detects and counts vehicles in traffic videos with 67-96% accuracy and high F1 scores for cars and trucks.
citing papers explorer
-
Clip-level Uncertainty and Temporal-aware Active Learning for End-to-End Multi-Object Tracking
CUTAL scores multi-frame clips for uncertainty and enforces temporal diversity to train transformer MOT models to near full-supervision performance with 50% of the labels.
-
CityOS: Privacy Architecture for Urban Sensing
CityOS is an edge runtime that enforces a three-tier privacy API for urban sensors: local raw data, differentially private single-location stats, and cross-location aggregates with per-user budgets enforced on devices.
-
Learned Nonlocal Feature Matching and Filtering for RAW Image Denoising
A learnable nonlocal block that mimics classical neighbor matching and collaborative filtering on multiscale features produces competitive RAW denoising with far fewer parameters than current deep models and generalizes across sensors.
-
Towards Unconstrained Human-Object Interaction
Introduces the U-HOI task and shows MLLMs plus a language-to-graph pipeline can handle human-object interactions without any predefined vocabulary at training or inference time.
-
STORM: End-to-End Referring Multi-Object Tracking in Videos
STORM is an end-to-end MLLM for referring multi-object tracking that uses task-composition learning to leverage sub-task data and introduces the STORM-Bench dataset, achieving SOTA results.
-
OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedback
OmniTrack++ improves omnidirectional multi-object tracking with trajectory feedback through DynamicSSM stabilization, FlexiTrack instances, ExpertTrack Memory with Mixture-of-Experts, and adaptive Tracklet Management, achieving SOTA HOTA gains on JRDB and new EmboTrack benchmark.
-
Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object Tracking
A graph neural network framework learns affinities from appearance and motion then solves bipartite matching for online multiple-object tracking.
-
ERPPO: Entropy Regularization-based Proximal Policy Optimization
ERPPO adds a DSA-based ambiguity estimator to MAPPO and switches between L1 and L2 entropy regularization to improve exploration and stability in non-stationary multi-dimensional observations.
-
Occlusion-Aware Multi-Object Tracking via Expected Probability of Detection
The paper derives an occlusion-aware multi-object tracking method that assigns each object an expected detection probability over the reduced Palm density within a multi-Bernoulli mixture filter.
-
SAMOFT: Robust Multi-Object Tracking via Region and Flow
SAMOFT improves multi-object tracking by using SAM segmentation and optical flow for pixel-level motion matching, flexible centroid correction, and training-free motion pattern fixes on top of standard Kalman and ReID baselines.
-
Time-series Meets Complex Motion Modeling: Robust and Computational-effective Motion Predictor for Multi-object Tracking
TCMP achieves SOTA MOT metrics (HOTA 63.4%, IDF1 65.0%, AssA 49.1%) with 0.014x parameters and 0.05x FLOPs of the previous best method by using a simple dilated TCN regressor.
-
Lightweight Distillation of SAM 3 and DINOv3 for Edge-Deployable Individual-Level Livestock Monitoring and Longitudinal Visual Analytics
Distilled SAM 3 and DINOv3 models deliver near-teacher accuracy in pig tracking (92.29% MOTA, 96.15% IDF1) and behavior classification while achieving 7.77x parameter reduction and fitting on Jetson Orin NX with headroom.
-
Hypergraph-State Collaborative Reasoning for Multi-Object Tracking
HyperSSM integrates hypergraphs and state space models to let correlated objects mutually refine motion estimates, stabilizing trajectories under noise and occlusion for state-of-the-art multi-object tracking.
-
Attention Is not Everything: Efficient Alternatives for Vision
A survey that taxonomizes non-Transformer vision models and evaluates their practical trade-offs across efficiency, scalability, and robustness.
-
Intelligent Traffic Monitoring with YOLOv11: A Case Study in Real-Time Vehicle Detection
A YOLOv11-based desktop application detects and counts vehicles in traffic videos with 67-96% accuracy and high F1 scores for cars and trucks.