{"total":42,"rows":[{"id":"2101.05068","title":"Probabilistic Embeddings for Cross-Modal Retrieval","created":"2021-01-13","cited_by_count":151,"area":null},{"id":"2106.03849","title":"SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition","created":"2021-06-07","cited_by_count":69,"area":null},{"id":"2306.05526","title":"Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment","created":"2023-06-08","cited_by_count":46,"area":null},{"id":"2210.07503","title":"STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition","created":"2022-10-14","cited_by_count":43,"area":null},{"id":"2305.18171","title":"Improved Probabilistic Image-Text Representations","created":"2023-05-29","cited_by_count":40,"area":null},{"id":"2107.08580","title":"UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition","created":"2021-07-19","cited_by_count":35,"area":null},{"id":"2112.07088","title":"ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses","created":"2021-12-14","cited_by_count":35,"area":null},{"id":"2204.03946","title":"Probabilistic Representations for Video Contrastive Learning","created":"2022-04-08","cited_by_count":34,"area":null},{"id":"2403.12534","title":"ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More","created":"2024-03-19","cited_by_count":33,"area":null},{"id":"2104.02710","title":"The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactions","created":"2021-04-06","cited_by_count":31,"area":null},{"id":"2109.01305","title":"Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition","created":"2021-09-03","cited_by_count":29,"area":null},{"id":"2110.00280","title":"Generalizable Human Pose Triangulation","created":"2021-10-01","cited_by_count":24,"area":null},{"id":"2112.05121","title":"Self-Supervised Keypoint Discovery in Behavioral Videos","created":"2021-12-09","cited_by_count":23,"area":null},{"id":"2209.00065","title":"ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting","created":"2022-08-31","cited_by_count":22,"area":null},{"id":"2212.05638","title":"Cross-Modal Learning with 3D Deformable Attention for Action Recognition","created":"2022-12-12","cited_by_count":20,"area":null},{"id":"2112.05892","title":"COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality","created":"2021-12-11","cited_by_count":19,"area":null},{"id":"2407.04458","title":"Robust Multimodal Learning via Representation Decoupling","created":"2024-07-05","cited_by_count":17,"area":null},{"id":"2206.11895","title":"Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space","created":"2022-06-23","cited_by_count":13,"area":null},{"id":"2408.02138","title":"RICA2: Rubric-Informed, Calibrated Assessment of Actions","created":"2024-08-04","cited_by_count":13,"area":null},{"id":"2204.09434","title":"FenceNet: Fine-grained Footwork Recognition in Fencing","created":"2022-04-20","cited_by_count":12,"area":null},{"id":"2204.12223","title":"Context-Aware Sequence Alignment using 4D Skeletal Augmentation","created":"2022-04-26","cited_by_count":11,"area":null},{"id":"2302.01332","title":"Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval","created":"2023-02-02","cited_by_count":10,"area":null},{"id":"2403.05856","title":"POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-View World","created":"2024-03-09","cited_by_count":10,"area":null},{"id":"2309.09982","title":"Introspective Deep Metric Learning","created":"2023-09-11","cited_by_count":7,"area":null},{"id":"2402.06150","title":"Domain Generalization with Small Data","created":"2024-02-09","cited_by_count":6,"area":null},{"id":"2305.07910","title":"Mask to reconstruct: Cooperative Semantics Completion for Video-text Retrieval","created":"2023-05-13","cited_by_count":5,"area":null},{"id":"2310.17049","title":"Learning Repeatable Speech Embeddings Using An Intra-class Correlation Regularizer","created":"2023-10-25","cited_by_count":3,"area":null},{"id":"2407.07092","title":"V-VIPE: Variational View Invariant Pose Embedding","created":"2024-07-09","cited_by_count":3,"area":null},{"id":"2211.08349","title":"Probabilistic Deep Metric Learning for Hyperspectral Image Classification","created":"2022-11-15","cited_by_count":2,"area":null},{"id":"2410.20427","title":"YourSkatingCoach: A Figure Skating Video Benchmark for Fine-Grained Element Analysis","created":"2024-10-27","cited_by_count":2,"area":null},{"id":"2102.04075","title":"Fast and Reliable Probabilistic Face Embeddings in the Wild","created":"2021-02-08","cited_by_count":1,"area":null},{"id":"2109.09299","title":"Semi-supervised Dense Keypoints Using Unlabeled Multiview Images","created":"2021-09-20","cited_by_count":1,"area":null},{"id":"2410.19349","title":"pEBR: A Probabilistic Approach to Embedding Based Retrieval","created":"2024-10-25","cited_by_count":1,"area":null},{"id":"2607.05271","title":"Target-Guided Selective Reweighting for Physics-Informed Neural Network Inverse Problems: A Transfer Learning Approach","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2106.12993","title":"Evaluation of deep lift pose models for 3D rodent pose estimation based on geometrically triangulated data","created":"2021-06-24","cited_by_count":0,"area":null},{"id":"2204.02710","title":"Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddings","created":"2022-04-06","cited_by_count":0,"area":null},{"id":"2205.04449","title":"Introspective Deep Metric Learning for Image Retrieval","created":"2022-05-09","cited_by_count":0,"area":null},{"id":"2309.04750","title":"Mirror-Aware Neural Humans","created":"2023-09-09","cited_by_count":0,"area":null},{"id":"2508.10281","title":"VIFSS: View-Invariant and Figure Skating-Specific Pose Representation Learning for Temporal Action Segmentation","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2510.15470","title":"MSAM: Multi-Semantic Adaptive Mining for Cross-Modal Drone Video-Text Retrieval","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2604.22839","title":"From Skeletons to Pixels: Few-Shot Precise Event Spotting via Representation and Prediction Distillation","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.22697","title":"Cross-Domain Human Action Recognition from Multiview Motion and Textual Descriptions","created":"2026-05-21","cited_by_count":0,"area":null}],"next_cursor":null}