{"total":45,"rows":[{"id":"2110.12951","title":"Seeing biodiversity: perspectives in machine learning for wildlife conservation","created":"2021-10-25","cited_by_count":130,"area":null},{"id":"2203.13250","title":"Global Tracking Transformers","created":"2022-03-24","cited_by_count":110,"area":null},{"id":"2105.03494","title":"The iWildCam 2021 Competition Dataset","created":"2021-05-07","cited_by_count":77,"area":null},{"id":"2104.09496","title":"Temporal Query Networks for Fine-grained Video Understanding","created":"2021-04-19","cited_by_count":68,"area":null},{"id":"2203.07363","title":"Implicit Motion Handling for Video Camouflaged Object Detection","created":"2022-03-14","cited_by_count":60,"area":null},{"id":"2101.08158","title":"Focal and Efficient IOU Loss for Accurate Bounding Box Regression","created":"2021-01-20","cited_by_count":57,"area":null},{"id":"2111.01024","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","created":"2021-11-01","cited_by_count":41,"area":null},{"id":"2112.06751","title":"Role of Human-AI Interaction in Selective Prediction","created":"2021-12-13","cited_by_count":35,"area":null},{"id":"2103.00560","title":"Perspectives on individual animal identification from biology and computer vision","created":"2021-02-28","cited_by_count":31,"area":null},{"id":"2111.14562","title":"Instance-wise Occlusion and Depth Orders in Natural Scenes","created":"2021-11-29","cited_by_count":31,"area":null},{"id":"2103.15632","title":"Regular Polytope Networks","created":"2021-03-29","cited_by_count":24,"area":null},{"id":"2302.05011","title":"Context Understanding in Computer Vision: A Survey","created":"2023-02-10","cited_by_count":23,"area":null},{"id":"2204.01184","title":"Exploiting Temporal Relations on Radar Perception for Autonomous Driving","created":"2022-04-03","cited_by_count":22,"area":null},{"id":"2203.15230","title":"Zero-Query Transfer Attacks on Context-Aware Object Detectors","created":"2022-03-29","cited_by_count":17,"area":null},{"id":"2108.06435","title":"Focus on the Positives: Self-Supervised Learning for Biodiversity Monitoring","created":"2021-08-14","cited_by_count":16,"area":null},{"id":"2112.06447","title":"SVIP: Sequence VerIfication for Procedures in Videos","created":"2021-12-13","cited_by_count":16,"area":null},{"id":"2503.18223","title":"MammAlps: A multi-view video behavior monitoring dataset of wild mammals in the Swiss Alps","created":"2025-03-23","cited_by_count":14,"area":null},{"id":"2204.05023","title":"Machine Learning and Deep Learning -- A review for Ecologists","created":"2022-04-11","cited_by_count":11,"area":null},{"id":"2406.05802","title":"SAM-PM: Enhancing Video Camouflaged Object Detection using Spatio-Temporal Attention","created":"2024-06-09","cited_by_count":11,"area":null},{"id":"2205.00275","title":"Dynamic Curriculum Learning for Great Ape Detection in the Wild","created":"2022-04-30","cited_by_count":10,"area":null},{"id":"2308.07050","title":"Survey on video anomaly detection in dynamic scenes with moving cameras","created":"2023-08-14","cited_by_count":10,"area":null},{"id":"2206.03666","title":"Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking","created":"2022-06-08","cited_by_count":9,"area":null},{"id":"2106.15083","title":"ElephantBook: A Semi-Automated Human-in-the-Loop System for Elephant Re-Identification","created":"2021-06-29","cited_by_count":8,"area":null},{"id":"2212.00266","title":"Multi-view Tracking, Re-ID, and Social Network Analysis of a Flock of Visually Similar Birds in an Outdoor Aviary","created":"2022-12-01","cited_by_count":7,"area":null},{"id":"2206.00718","title":"Context-Driven Detection of Invertebrate Species in Deep-Sea Video","created":"2022-06-01","cited_by_count":6,"area":null},{"id":"2301.04460","title":"Fast spline detection in high density microscopy data","created":"2023-01-11","cited_by_count":4,"area":null},{"id":"2210.04341","title":"ConTra: (Con)text (Tra)nsformer for Cross-Modal Video Retrieval","created":"2022-10-09","cited_by_count":3,"area":null},{"id":"2308.01630","title":"Erasure-based Interaction Network for RGBT Video Object Detection and A Unified Benchmark","created":"2023-08-03","cited_by_count":3,"area":null},{"id":"2408.14348","title":"Deep learning-based ecological analysis of camera trap images is impacted by training data quality and quantity","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2508.21809","title":"VoCap: Video Object Captioning and Segmentation from Any Prompt","created":"2025-08-29","cited_by_count":3,"area":null},{"id":"2104.06826","title":"Towards Automatic Model Specialization for Edge Video Analytics","created":"2021-04-14","cited_by_count":2,"area":null},{"id":"2111.06830","title":"Small or Far Away? Exploiting Deep Super-Resolution and Altitude Data for Aerial Animal Surveillance","created":"2021-11-12","cited_by_count":2,"area":null},{"id":"2303.04068","title":"VOCALExplore: Pay-as-You-Go Video Data Exploration and Model Building [Technical Report]","created":"2023-03-07","cited_by_count":2,"area":null},{"id":"2106.12212","title":"Image-to-Image Translation of Synthetic Samples for Rare Classes","created":"2021-06-23","cited_by_count":1,"area":null},{"id":"2111.02042","title":"Recent Advancements in Self-Supervised Paradigms for Visual Feature Representation","created":"2021-11-03","cited_by_count":1,"area":null},{"id":"2408.06636","title":"Unified-IoU: For High-Quality Object Detection","created":"2024-08-13","cited_by_count":1,"area":null},{"id":"2410.13616","title":"Spatiotemporal Object Detection for Improved Aerial Vehicle Detection in Traffic Monitoring","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2412.00290","title":"Adapting the re-ID challenge for static sensors","created":"2024-11-30","cited_by_count":1,"area":null},{"id":"2103.13428","title":"TagMe: GPS-Assisted Automatic Object Annotation in Videos","created":"2021-03-24","cited_by_count":0,"area":null},{"id":"2104.13763","title":"LGA-RCNN: Loss-Guided Attention for Object Detection","created":"2021-04-28","cited_by_count":0,"area":null},{"id":"2109.12040","title":"From images in the wild to video-informed image classification","created":"2021-09-24","cited_by_count":0,"area":null},{"id":"2401.13596","title":"PLATE: A perception-latency aware estimator,","created":"2024-01-24","cited_by_count":0,"area":null},{"id":"2504.11262","title":"Enhanced Small Target Detection via Multi-Modal Fusion and Attention Mechanisms: A YOLOv5 Approach","created":"2025-04-15","cited_by_count":0,"area":null},{"id":"2510.26681","title":"Improving Classification of Occluded Objects through Scene Context","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2512.16133","title":"Interaction-via-Actions: Cattle Interaction Detection with Joint Learning of Action-Interaction Latent Space","created":"2025-12-18","cited_by_count":0,"area":null}],"next_cursor":null}