Data to 14 Oct 2026

Learning Multi-Domain Convolutional Neural Networks for Visual Tracking

arXiv 1510.07945 ↗First posted 27 Oct 2015cs.CVcited by 209

Not on the map. Why?

Abstract (arXiv)

We propose a novel visual tracking algorithm based on the representations from a discriminatively trained Convolutional Neural Network (CNN). Our algorithm pretrains a CNN using a large set of videos with tracking ground-truths to obtain a generic target representation. Our network is composed of shared layers and multiple branches of domain-specific layers, where domains correspond to individual training sequences and each branch is responsible for binary classification to identify the target in each domain. We train the network with respect to each domain iteratively to obtain generic target representations in the shared layers. When tracking a target in a new sequence, we construct a new network by combining the shared layers in the pretrained CNN with a new binary classification layer, which is updated online. Online tracking is performed by evaluating the candidate windows randomly sampled around the previous target state. The proposed algorithm illustrates outstanding performance compared with state-of-the-art methods in existing tracking benchmarks.

Key facts. Cited by 209 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 Oct 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 75; 2022: 43; 2023: 35; 2024: 26; 2025: 20; 2026: 10.

209 papers.

Sort:

By area:

2021Transformer Trackingcited by 412
2021Learning Spatio-Temporal Transformer for Visual Trackingcited by 350
2022Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Frameworkcited by 330
2022MixFormer: End-to-End Tracking with Iterative Mixed Attentioncited by 281
2021Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Trackingcited by 220
2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
2021Towards Long-Form Video Understandingcited by 146
2021Learning Target Candidate Association to Keep Track of What Not to Trackcited by 131
2021VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flowscited by 129
2021Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmarkcited by 126
2022Transforming Model Prediction for Trackingcited by 117
2022Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidationcited by 113

38 more

2021LasHeR: A Large-scale High-diversity Benchmark for RGBT Trackingcited by 96
2021Object Tracking by Jointly Exploiting Frame and Event Domaincited by 84
2021LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Searchcited by 82
2023Robust Object Modeling for Visual Trackingcited by 80
2024Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformerscited by 76
2022Transformer Tracking with Cyclic Shifting Window Attentioncited by 75
2023Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baselinecited by 73
2021Learn to Match: Automatic Matching Network Design for Visual Trackingcited by 67
2021DepthTrack : Unveiling the Power of RGBD Trackingcited by 67
2024OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuningcited by 65
2023On the Stability-Plasticity Dilemma of Class-Incremental Learningcited by 56
2022Revisiting Color-Event based Tracking: A Unified Network, Dataset, and Metriccited by 52
2023Compact Transformer Tracker with Correlative Masked Modelingcited by 50
2024Explicit Visual Prompts for Visual Object Trackingcited by 50
2024SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Trackingcited by 44
2023Frame-Event Alignment and Fusion Network for High Frame Rate Trackingcited by 43
2023Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackerscited by 43
2021FEAR: Fast, Efficient, Accurate and Robust Visual Trackercited by 38
2022Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Citiescited by 38
2021Non-IID data and Continual Learning processes in Federated Learning: A long road aheadcited by 36
2021Specificity-Preserving Federated Learning for MR Image Reconstructioncited by 35
2021MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Trackingcited by 32
2021Anti-UAV: A Large Multi-Modal Benchmark for UAV Trackingcited by 31
2022Unified Transformer Tracker for Object Trackingcited by 31
2021Unsupervised Visual Attention and Invariance for Reinforcement Learningcited by 30
2021Towards Distraction-Robust Active Visual Trackingcited by 30
2021Saliency-Associated Object Trackingcited by 30
2022WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Trackingcited by 26
2021IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Trackingcited by 25
2022Learning Target-aware Representation for Visual Tracking via Informative Interactionscited by 25
2022Visual Object Tracking in First Person Visioncited by 25
2022Efficient Visual Tracking via Hierarchical Cross-Attention Transformercited by 24
2025Exploring Decoupled Spatio-Temporal Consistency Learning and Self-Prompting Evolution for Self-Supervised Trackingcited by 23
2021Discriminative Appearance Modeling with Multi-track Pooling for Real-time Multi-object Trackingcited by 22
2023DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Taskscited by 22
2024Mamba-FETrack: Frame-Event Tracking via State Space Modelcited by 22
2021Learning to Track Objects from Unlabeled Videoscited by 21
2021Is First Person Vision Challenging for Object Tracking?cited by 21

50 most cited of 209 All 209 (JSON)