{"total":401,"rows":[{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429,"area":null},{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253,"area":null},{"id":"2206.08496","title":"Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency","created":"2022-06-17","cited_by_count":250,"area":null},{"id":"2104.05025","title":"New Insights on Reducing Abrupt Representation Change in Online Continual Learning","created":"2021-04-11","cited_by_count":219,"area":null},{"id":"2102.10757","title":"Self-Supervised Learning of Graph Neural Networks: A Unified Review","created":"2021-02-22","cited_by_count":184,"area":null},{"id":"2205.06743","title":"A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities","created":"2022-05-13","cited_by_count":163,"area":null},{"id":"2107.10912","title":"Explainable artificial intelligence (XAI) in deep learning-based medical image analysis","created":"2021-07-22","cited_by_count":147,"area":null},{"id":"2108.07960","title":"SynFace: Face Recognition with Synthetic Data","created":"2021-08-18","cited_by_count":106,"area":null},{"id":"2210.10239","title":"GSV-Cities: Toward Appropriate Supervised Visual Place Recognition","created":"2022-10-19","cited_by_count":93,"area":null},{"id":"2109.14910","title":"CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations","created":"2021-09-30","cited_by_count":72,"area":null},{"id":"2204.10704","title":"SUES-200: A Multi-height Multi-scene Cross-view Image Benchmark Across Drone and Satellite","created":"2022-04-22","cited_by_count":64,"area":null},{"id":"2106.03609","title":"High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning","created":"2021-06-07","cited_by_count":54,"area":null},{"id":"2307.09484","title":"MolFM: A Multimodal Molecular Foundation Model","created":"2023-06-06","cited_by_count":50,"area":null},{"id":"2303.13199","title":"First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning","created":"2023-03-23","cited_by_count":46,"area":null},{"id":"2203.02195","title":"Voice-Face Homogeneity Tells Deepfake","created":"2022-03-04","cited_by_count":44,"area":null},{"id":"2206.12772","title":"Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation","created":"2022-06-26","cited_by_count":44,"area":null},{"id":"2207.10362","title":"LocVTP: Video-Text Pre-training for Temporal Localization","created":"2022-07-21","cited_by_count":44,"area":null},{"id":"2104.05845","title":"Visual Goal-Step Inference using wikiHow","created":"2021-04-12","cited_by_count":43,"area":null},{"id":"2112.07957","title":"FEAR: Fast, Efficient, Accurate and Robust Visual Tracker","created":"2021-12-15","cited_by_count":38,"area":null},{"id":"2101.08333","title":"Zero-shot Generalization in Dialog State Tracking through Generative Question Answering","created":"2021-01-20","cited_by_count":33,"area":null},{"id":"2203.08615","title":"Scientific and Technological Information Oriented Semantics-adversarial and Media-adversarial Cross-media Retrieval","created":"2022-03-16","cited_by_count":33,"area":null},{"id":"2305.16373","title":"DeepGate2: Functionality-Aware Circuit Representation Learning","created":"2023-05-25","cited_by_count":33,"area":null},{"id":"2202.03007","title":"Learning Sound Localization Better From Semantically Similar Samples","created":"2022-02-07","cited_by_count":32,"area":null},{"id":"2203.16291","title":"AmsterTime: A Visual Place Recognition Benchmark Dataset for Severe Domain Shift","created":"2022-03-30","cited_by_count":32,"area":null},{"id":"2309.10724","title":"Sound Source Localization is All about Cross-Modal Alignment","created":"2023-09-19","cited_by_count":31,"area":null},{"id":"2309.11433","title":"A Systematic Review of Few-Shot Learning in Medical Imaging","created":"2023-09-20","cited_by_count":28,"area":null},{"id":"2104.08481","title":"Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes","created":"2021-04-17","cited_by_count":27,"area":null},{"id":"2308.05667","title":"2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Clouds","created":"2023-08-10","cited_by_count":27,"area":null},{"id":"2202.14019","title":"Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment","created":"2022-02-28","cited_by_count":25,"area":null},{"id":"2103.15632","title":"Regular Polytope Networks","created":"2021-03-29","cited_by_count":24,"area":null},{"id":"2108.05887","title":"Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations","created":"2021-08-12","cited_by_count":24,"area":null},{"id":"2108.09468","title":"End2End Occluded Face Recognition by Masking Corrupted Features","created":"2021-08-21","cited_by_count":24,"area":null},{"id":"2204.00157","title":"LASER: LAtent SpacE Rendering for 2D Visual Localization","created":"2022-04-01","cited_by_count":24,"area":null},{"id":"2106.06620","title":"Robust Representation Learning via Perceptual Similarity Metrics","created":"2021-06-11","cited_by_count":23,"area":null},{"id":"2107.02396","title":"Semi-TCL: Semi-Supervised Track Contrastive Representation Learning","created":"2021-07-06","cited_by_count":23,"area":null},{"id":"2111.00970","title":"Hex2vec -- Context-Aware Embedding H3 Hexagons with OpenStreetMap Tags","created":"2021-11-01","cited_by_count":23,"area":null},{"id":"2112.04323","title":"Contrastive Learning with Large Memory Bank and Negative Embedding Subtraction for Accurate Copy Detection","created":"2021-12-08","cited_by_count":23,"area":null},{"id":"2104.11507","title":"DeepfakeUCL: Deepfake Detection via Unsupervised Contrastive Learning","created":"2021-04-23","cited_by_count":20,"area":null},{"id":"2210.11557","title":"Learning Attention Propagation for Compositional Zero-Shot Learning","created":"2022-10-20","cited_by_count":20,"area":null},{"id":"2202.04731","title":"Graph Neural Network for Cell Tracking in Microscopy Videos","created":"2022-02-09","cited_by_count":19,"area":null},{"id":"2103.04046","title":"Simplicial Complex Representation Learning","created":"2021-03-06","cited_by_count":17,"area":null},{"id":"2104.10068","title":"Contrastive Learning for Sports Video: Unsupervised Player Classification","created":"2021-04-15","cited_by_count":17,"area":null},{"id":"2109.09740","title":"Neural Distance Embeddings for Biological Sequences","created":"2021-09-20","cited_by_count":17,"area":null},{"id":"2109.15031","title":"Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attacks","created":"2021-09-29","cited_by_count":16,"area":null},{"id":"2211.09920","title":"Distributed Deep Joint Source-Channel Coding over a Multiple Access Channel","created":"2022-11-17","cited_by_count":16,"area":null},{"id":"2407.13555","title":"PetFace: A Large-Scale Dataset and Benchmark for Animal Identification","created":"2024-07-18","cited_by_count":16,"area":null},{"id":"2206.15478","title":"On the Learning and Learnability of Quasimetrics","created":"2022-06-30","cited_by_count":15,"area":null},{"id":"2207.08664","title":"Action-based Contrastive Learning for Trajectory Prediction","created":"2022-07-18","cited_by_count":15,"area":null},{"id":"2212.01985","title":"ObjectMatch: Robust Registration using Canonical Object Correspondences","created":"2022-12-05","cited_by_count":15,"area":null},{"id":"2301.05579","title":"A survey and taxonomy of loss functions in machine learning","created":"2023-01-13","cited_by_count":15,"area":null},{"id":"2410.23413","title":"EchoFM: Foundation Model for Generalizable Echocardiogram Analysis","created":"2024-10-30","cited_by_count":15,"area":null},{"id":"2102.05749","title":"Self-Supervised VQ-VAE for One-Shot Music Style Transfer","created":"2021-02-10","cited_by_count":14,"area":null},{"id":"2105.11113","title":"Dynamic Class Queue for Large Scale Face Recognition In the Wild","created":"2021-05-24","cited_by_count":14,"area":null},{"id":"2105.03746","title":"Contrastive Attraction and Contrastive Repulsion for Representation Learning","created":"2021-05-08","cited_by_count":13,"area":null},{"id":"2106.10458","title":"Place recognition survey: An update on deep learning approaches","created":"2021-06-19","cited_by_count":13,"area":null},{"id":"2109.07455","title":"Deep Bregman Divergence for Contrastive Learning of Visual Representations","created":"2021-09-15","cited_by_count":13,"area":null},{"id":"2207.13479","title":"AutoTransition: Learning to Recommend Video Transition Effects","created":"2022-07-27","cited_by_count":13,"area":null},{"id":"2401.09942","title":"Multi-task Learning for Joint Re-identification, Team Affiliation, and Role Classification for Sports Visual Tracking","created":"2024-01-18","cited_by_count":13,"area":null},{"id":"2101.11059","title":"Event-Driven News Stream Clustering using Entity-Aware Contextual Embeddings","created":"2021-01-26","cited_by_count":12,"area":null},{"id":"2103.05585","title":"SimTriplet: Simple Triplet Representation Learning with a Single GPU","created":"2021-03-09","cited_by_count":12,"area":null},{"id":"2103.15573","title":"HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences","created":"2021-03-29","cited_by_count":12,"area":null},{"id":"2210.04050","title":"Multi-Modal Human Authentication Using Silhouettes, Gait and RGB","created":"2022-10-08","cited_by_count":12,"area":null},{"id":"2211.01407","title":"On the Informativeness of Supervision Signals","created":"2022-11-02","cited_by_count":12,"area":null},{"id":"2309.05310","title":"ImitationNet: Unsupervised Human-to-Robot Motion Retargeting via Shared Latent Space","created":"2023-09-11","cited_by_count":12,"area":null},{"id":"2109.13576","title":"Multimodality in Meta-Learning: A Comprehensive Survey","created":"2021-09-28","cited_by_count":11,"area":null},{"id":"2201.09650","title":"What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradiction","created":"2022-01-24","cited_by_count":11,"area":null},{"id":"2203.12748","title":"Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning","created":"2022-03-23","cited_by_count":11,"area":null},{"id":"2211.14394","title":"Link Prediction with Non-Contrastive Learning","created":"2022-11-25","cited_by_count":11,"area":null},{"id":"2305.19730","title":"Data Representations' Study of Latent Image Manifolds","created":"2023-05-31","cited_by_count":11,"area":null},{"id":"2104.01989","title":"Dr-Vectors: Decision Residual Networks and an Improved Loss for Speaker Recognition","created":"2021-04-05","cited_by_count":10,"area":null},{"id":"2104.06806","title":"Continual learning in cross-modal retrieval","created":"2021-04-14","cited_by_count":10,"area":null},{"id":"2201.09267","title":"Spectral, Probabilistic, and Deep Metric Learning: Tutorial and Survey","created":"2022-01-23","cited_by_count":10,"area":null},{"id":"2309.12501","title":"Knowledge Graph Embedding: An Overview","created":"2023-09-21","cited_by_count":10,"area":null},{"id":"2408.10919","title":"CrossFi: A Cross Domain Wi-Fi Sensing Framework Based on Siamese Network","created":"2024-08-20","cited_by_count":10,"area":null},{"id":"2412.13364","title":"Bringing Multimodality to Amazon Visual Search System","created":"2024-12-17","cited_by_count":10,"area":null},{"id":"2104.06524","title":"Holistic Guidance for Occluded Person Re-Identification","created":"2021-04-13","cited_by_count":9,"area":null},{"id":"2105.03647","title":"Informative and Representative Triplet Selection for Multilabel Remote Sensing Image Retrieval","created":"2021-05-08","cited_by_count":9,"area":null},{"id":"2109.00951","title":"GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps","created":"2021-09-02","cited_by_count":9,"area":null},{"id":"2203.01153","title":"InsertionNet 2.0: Minimal Contact Multi-Step Insertion Using Multimodal Multiview Sensory Input","created":"2022-03-02","cited_by_count":9,"area":null},{"id":"2208.04163","title":"Abstractive Meeting Summarization: A Survey","created":"2022-08-08","cited_by_count":9,"area":null},{"id":"2302.13033","title":"Speaker Recognition in Realistic Scenario Using Multimodal Data","created":"2023-02-25","cited_by_count":9,"area":null},{"id":"2306.14662","title":"Cross Architecture Distillation for Face Recognition","created":"2023-06-26","cited_by_count":9,"area":null},{"id":"2507.10583","title":"$\\texttt{Droid}$: A Resource Suite for AI-Generated Code Detection","created":"2025-07-11","cited_by_count":9,"area":null},{"id":"2101.03292","title":"Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning","created":"2021-01-09","cited_by_count":8,"area":null},{"id":"2104.05072","title":"Instagram Filter Removal on Fashionable Images","created":"2021-04-11","cited_by_count":8,"area":null},{"id":"2107.06187","title":"Deep Ranking with Adaptive Margin Triplet Loss","created":"2021-07-13","cited_by_count":8,"area":null},{"id":"2111.00006","title":"Adaptive Hierarchical Similarity Metric Learning with Noisy Labels","created":"2021-10-29","cited_by_count":8,"area":null},{"id":"2202.01897","title":"AtmoDist: Self-supervised Representation Learning for Atmospheric Dynamics","created":"2022-02-02","cited_by_count":8,"area":null},{"id":"2204.04813","title":"Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2206.03012","title":"TriBYOL: Triplet BYOL for Self-Supervised Representation Learning","created":"2022-06-07","cited_by_count":8,"area":null},{"id":"2209.13262","title":"Exploring the Algorithm-Dependent Generalization of AUPRC Optimization with List Stability","created":"2022-09-27","cited_by_count":8,"area":null},{"id":"2211.03989","title":"$BT^2$: Backward-compatible Training with Basis Transformation","created":"2022-11-08","cited_by_count":8,"area":null},{"id":"2211.07116","title":"Few-shot Metric Learning: Online Adaptation of Embedding for Retrieval","created":"2022-11-14","cited_by_count":8,"area":null},{"id":"2301.07284","title":"Label Inference Attack against Split Learning under Regression Setting","created":"2023-01-18","cited_by_count":8,"area":null},{"id":"2309.04675","title":"BiLMa: Bidirectional Local-Matching for Text-based Person Re-identification","created":"2023-09-09","cited_by_count":8,"area":null},{"id":"2310.05615","title":"Adaptive Multi-head Contrastive Learning","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2311.16497","title":"GaitContour: Efficient Gait Recognition based on a Contour-Pose Representation","created":"2023-11-27","cited_by_count":8,"area":null},{"id":"2402.14957","title":"The Common Stability Mechanism behind most Self-Supervised Learning Approaches","created":"2024-02-22","cited_by_count":8,"area":null},{"id":"2407.13676","title":"Aligning Sight and Sound: Advanced Sound Source Localization Through Audio-Visual Alignment","created":"2024-07-18","cited_by_count":8,"area":null},{"id":"2408.05920","title":"Urban Region Pre-training and Prompting: A Graph-based Approach","created":"2024-08-12","cited_by_count":8,"area":null}],"next_cursor":"100"}