{"list":"other","total":52,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"1907.09682","title":"Similarity-Preserving Knowledge Distillation","created":"2019-07-23","cited_by_count":516},{"id":"1810.11981","title":"GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild","created":"2018-10-29","cited_by_count":475},{"id":"1809.07845","title":"LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking","created":"2018-09-20","cited_by_count":429},{"id":"2103.15436","title":"Transformer Tracking","created":"2021-03-29","cited_by_count":412},{"id":"2203.08679","title":"Decoupled Knowledge Distillation","created":"2022-03-16","cited_by_count":388},{"id":"2103.17154","title":"Learning Spatio-Temporal Transformer for Visual Tracking","created":"2021-03-31","cited_by_count":350},{"id":"1904.07220","title":"Learning Discriminative Model Prediction for Tracking","created":"2019-04-15","cited_by_count":344},{"id":"1803.10794","title":"TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild","created":"2018-03-28","cited_by_count":343},{"id":"2203.11991","title":"Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework","created":"2022-03-22","cited_by_count":330},{"id":"1811.07628","title":"ATOM: Accurate Tracking by Overlap Maximization","created":"2018-11-19","cited_by_count":285},{"id":"2203.11082","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2022-03-21","cited_by_count":281},{"id":"1903.04197","title":"Structured Knowledge Distillation for Dense Prediction","created":"2019-03-11","cited_by_count":279},{"id":"1812.05050","title":"Fast Online Object Tracking and Segmentation: A Unifying Approach","created":"2018-12-12","cited_by_count":272},{"id":"2003.12565","title":"Probabilistic Regression for Visual Tracking","created":"2020-03-27","cited_by_count":231},{"id":"1510.07945","title":"Learning Multi-Domain Convolutional Neural Networks for Visual Tracking","created":"2015-10-27","cited_by_count":209},{"id":"1911.12836","title":"Siam R-CNN: Visual Tracking by Re-Detection","created":"2019-11-28","cited_by_count":174},{"id":"2011.13256","title":"Channel-wise Knowledge Distillation for Dense Prediction","created":"2020-11-26","cited_by_count":163},{"id":"2303.10826","title":"Visual Prompt Multi-Modal Tracking","created":"2023-03-20","cited_by_count":142},{"id":"2108.05015","title":"VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows","created":"2021-08-11","cited_by_count":129},{"id":"2104.13202","title":"LasHeR: A Large-scale High-diversity Benchmark for RGBT Tracking","created":"2021-04-27","cited_by_count":96},{"id":"2104.14545","title":"LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search","created":"2021-04-29","cited_by_count":82},{"id":"2004.00305","title":"High-Performance Long-Term Tracking with Meta-Updater","created":"2020-04-01","cited_by_count":80},{"id":"2108.13962","title":"DepthTrack : Unveiling the Power of RGBD Tracking","created":"2021-08-31","cited_by_count":67},{"id":"1804.04273","title":"VITAL: VIsual Tracking via Adversarial Learning","created":"2018-04-12","cited_by_count":65},{"id":"2311.15851","title":"Single-Model and Any-Modality for Video Object Tracking","created":"2023-11-27","cited_by_count":65},{"id":"2403.09634","title":"OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning","created":"2024-03-14","cited_by_count":65},{"id":"2203.01666","title":"Correlation-Aware Deep Tracking","created":"2022-03-03","cited_by_count":62},{"id":"2207.14571","title":"Prompting for Multi-Modal Tracking","created":"2022-07-29","cited_by_count":59},{"id":"2305.15896","title":"MixFormerV2: Efficient Fully Transformer Tracking","created":"2023-05-25","cited_by_count":57},{"id":"2412.15691","title":"Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking","created":"2024-12-20","cited_by_count":57},{"id":"2007.13143","title":"Challenge-Aware RGBT Tracking","created":"2020-07-26","cited_by_count":53},{"id":"2412.19138","title":"SUTrack: Towards Simple and Unified Single Object Tracking","created":"2024-12-26","cited_by_count":52},{"id":"2007.02041","title":"Jointly Modeling Motion and Appearance Cues for Robust RGB-T Tracking","created":"2020-07-04","cited_by_count":48},{"id":"2312.10611","title":"Bi-directional Adapter for Multi-modal Tracking","created":"2023-12-17","cited_by_count":46},{"id":"2307.04129","title":"Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackers","created":"2023-07-09","cited_by_count":43},{"id":"2208.09787","title":"RGBD1K: A Large-scale Dataset and Benchmark for RGB-D Object Tracking","created":"2022-08-21","cited_by_count":42},{"id":"1907.10451","title":"Dense Feature Aggregation and Pruning for RGBT Tracking","created":"2019-07-24","cited_by_count":40},{"id":"2412.11023","title":"Exploring Enhanced Contextual Information for Video-Level Object Tracking","created":"2024-12-15","cited_by_count":37},{"id":"2410.10791","title":"CAFuser: Condition-Aware Multimodal Fusion for Robust Semantic Perception of Driving Scenes","created":"2024-10-14","cited_by_count":33},{"id":"1912.00660","title":"DAL -- A Deep Depth-aware Long-term Tracker","created":"2019-12-02","cited_by_count":26},{"id":"2211.12735","title":"Fast-iTPN: Integrally Pre-Trained Transformer Pyramid Network with Token Migration","created":"2022-11-23","cited_by_count":24},{"id":"2405.17773","title":"XTrack: Multimodal Training Boosts RGB-X Video Object Trackers","created":"2024-05-28","cited_by_count":21},{"id":"2107.08591","title":"Double Similarity Distillation for Semantic Image Segmentation","created":"2021-07-19","cited_by_count":19},{"id":"2309.09249","title":"LiteTrack: Layer Pruning with Asynchronous Feature Extraction for Lightweight and Efficient Visual Tracking","created":"2023-09-17","cited_by_count":16},{"id":"2507.05899","title":"What You Have is What You Track: Adaptive and Robust Multimodal Tracking","created":"2025-07-08","cited_by_count":15},{"id":"2408.10487","title":"MambaEVT: Event Stream based Visual Object Tracking using State Space Model","created":"2024-08-20","cited_by_count":12},{"id":"2503.18244","title":"CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation","created":"2025-03-23","cited_by_count":11}],"next_cursor":null}