{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/object-detection/papers/47","list_of":"/task/object-detection","task":"Object Detection","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":47,"pages_in_order":110,"rows_per_page":100,"rows":[4601,4700],"of":10957,"counts":{"archive_papers_tagged":10957,"with_a_code_link":4657,"where_syntology_ran_a_sample":1183,"not_listed_spam_title":0,"listed":10957,"listed_where_code_ran":1183,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1038,"every_run_a_failure_of_syntologys_instrument":145,"listed_with_a_run_with_no_instrument_failure":1038,"listed_every_run_a_failure_of_syntologys_instrument":145,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/object-detection","prev":"/task/object-detection/papers/46","next":"/task/object-detection/papers/48","papers":[{"url":"/paper/online-multi-object-tracking-via-robust","slug":"online-multi-object-tracking-via-robust","title":"Online multi-object tracking via robust collaborative model and sample selection","date":"2017-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/beyond-skip-connections-top-down-modulation","slug":"beyond-skip-connections-top-down-modulation","title":"Beyond Skip Connections: Top-Down Modulation for Object Detection","date":"2016-12-20","arxiv_id":"1612.06851","repositories_listed":1,"syntology":null},{"url":"/paper/learning-features-by-watching-objects-move","slug":"learning-features-by-watching-objects-move","title":"Learning Features by Watching Objects Move","date":"2016-12-19","arxiv_id":"1612.06370","repositories_listed":1,"syntology":null},{"url":"/paper/scenenet-rgb-d-5m-photorealistic-images-of","slug":"scenenet-rgb-d-5m-photorealistic-images-of","title":"SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground Truth","date":"2016-12-15","arxiv_id":"1612.05079","repositories_listed":1,"syntology":null},{"url":"/paper/spatially-adaptive-computation-time-for","slug":"spatially-adaptive-computation-time-for","title":"Spatially Adaptive Computation Time for Residual Networks","date":"2016-12-07","arxiv_id":"1612.02297","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/spatially-adaptive-computation-time-for#ran","syntology_url":"https://syntology.ai/paper/1612.02297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.02297"}},"official":{"repos":["mfigurnov/sact"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/playing-doom-with-slam-augmented-deep","slug":"playing-doom-with-slam-augmented-deep","title":"Playing Doom with SLAM-Augmented Deep Reinforcement Learning","date":"2016-12-01","arxiv_id":"1612.00380","repositories_listed":1,"syntology":null},{"url":"/paper/3d-fully-convolutional-network-for-vehicle","slug":"3d-fully-convolutional-network-for-vehicle","title":"3D Fully Convolutional Network for Vehicle Detection in Point Cloud","date":"2016-11-24","arxiv_id":"1611.08069","repositories_listed":1,"syntology":null},{"url":"/paper/straight-to-shapes-real-time-detection-of","slug":"straight-to-shapes-real-time-detection-of","title":"Straight to Shapes: Real-time Detection of Encoded Shapes","date":"2016-11-23","arxiv_id":"1611.07932","repositories_listed":1,"syntology":null},{"url":"/paper/deep-neural-networks-can-be-improved-using","slug":"deep-neural-networks-can-be-improved-using","title":"Deep neural networks can be improved using human-derived contextual expectations","date":"2016-11-22","arxiv_id":"1611.07218","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-object-detection-with-deep","slug":"hierarchical-object-detection-with-deep","title":"Hierarchical Object Detection with Deep Reinforcement Learning","date":"2016-11-11","arxiv_id":"1611.03718","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-people-in-artwork-with-cnns","slug":"detecting-people-in-artwork-with-cnns","title":"Detecting People in Artwork with CNNs","date":"2016-10-27","arxiv_id":"1610.08871","repositories_listed":1,"syntology":null},{"url":"/paper/stuffnet-using-stuff-to-improve-object","slug":"stuffnet-using-stuff-to-improve-object","title":"StuffNet: Using 'Stuff' to Improve Object Detection","date":"2016-10-19","arxiv_id":"1610.05861","repositories_listed":1,"syntology":null},{"url":"/paper/crafting-gbd-net-for-object-detection","slug":"crafting-gbd-net-for-object-detection","title":"Crafting GBD-Net for Object Detection","date":"2016-10-08","arxiv_id":"1610.02579","repositories_listed":1,"syntology":null},{"url":"/paper/deepskeleton-learning-multi-task-scale","slug":"deepskeleton-learning-multi-task-scale","title":"DeepSkeleton: Learning Multi-task Scale-associated Deep Side Outputs for Object Skeleton Extraction in Natural Images","date":"2016-09-13","arxiv_id":"1609.03659","repositories_listed":1,"syntology":null},{"url":"/paper/ubernet-training-a-universal-convolutional","slug":"ubernet-training-a-universal-convolutional","title":"UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory","date":"2016-09-07","arxiv_id":"1609.02132","repositories_listed":1,"syntology":null},{"url":"/paper/deep-retinal-image-understanding","slug":"deep-retinal-image-understanding","title":"Deep Retinal Image Understanding","date":"2016-09-05","arxiv_id":"1609.01103","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-multi-scale-deep-convolutional","slug":"a-unified-multi-scale-deep-convolutional","title":"A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection","date":"2016-07-25","arxiv_id":"1607.07155","repositories_listed":1,"syntology":null},{"url":"/paper/attend-refine-repeat-active-box-proposal","slug":"attend-refine-repeat-active-box-proposal","title":"Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization","date":"2016-06-14","arxiv_id":"1606.04446","repositories_listed":1,"syntology":null},{"url":"/paper/face-detection-with-the-faster-r-cnn","slug":"face-detection-with-the-faster-r-cnn","title":"Face Detection with the Faster R-CNN","date":"2016-06-10","arxiv_id":"1606.03473","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-salient-object-detection-with-a","slug":"real-time-salient-object-detection-with-a","title":"Real-Time Salient Object Detection With a Minimum Spanning Tree","date":"2016-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unconstrained-salient-object-detection-via","slug":"unconstrained-salient-object-detection-via","title":"Unconstrained Salient Object Detection via Proposal Subset Optimization","date":"2016-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/self-paced-deep-learning-for-weakly","slug":"self-paced-deep-learning-for-weakly","title":"Self Paced Deep Learning for Weakly Supervised Object Detection","date":"2016-05-24","arxiv_id":"1605.07651","repositories_listed":1,"syntology":null},{"url":"/paper/subcategory-aware-convolutional-neural","slug":"subcategory-aware-convolutional-neural","title":"Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection","date":"2016-04-16","arxiv_id":"1604.04693","repositories_listed":1,"syntology":null},{"url":"/paper/object-detection-from-video-tubelets-with","slug":"object-detection-from-video-tubelets-with","title":"Object Detection from Video Tubelets with Convolutional Neural Networks","date":"2016-04-14","arxiv_id":"1604.04053","repositories_listed":1,"syntology":null},{"url":"/paper/counting-everyday-objects-in-everyday-scenes","slug":"counting-everyday-objects-in-everyday-scenes","title":"Counting Everyday Objects in Everyday Scenes","date":"2016-04-12","arxiv_id":"1604.03505","repositories_listed":1,"syntology":null},{"url":"/paper/craft-objects-from-images","slug":"craft-objects-from-images","title":"CRAFT Objects from Images","date":"2016-04-12","arxiv_id":"1604.03239","repositories_listed":1,"syntology":null},{"url":"/paper/t-cnn-tubelets-with-convolutional-neural","slug":"t-cnn-tubelets-with-convolutional-neural","title":"T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos","date":"2016-04-09","arxiv_id":"1604.02532","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/t-cnn-tubelets-with-convolutional-neural#ran","syntology_url":"https://syntology.ai/paper/1604.02532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.02532"}},"official":{"repos":["myfavouritekk/T-CNN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-multipath-network-for-object-detection","slug":"a-multipath-network-for-object-detection","title":"A MultiPath Network for Object Detection","date":"2016-04-07","arxiv_id":"1604.02135","repositories_listed":1,"syntology":null},{"url":"/paper/image-captioning-with-deep-bidirectional","slug":"image-captioning-with-deep-bidirectional","title":"Image Captioning with Deep Bidirectional LSTMs","date":"2016-04-04","arxiv_id":"1604.00790","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-batch-normalization-for-practical","slug":"revisiting-batch-normalization-for-practical","title":"Revisiting Batch Normalization For Practical Domain Adaptation","date":"2016-03-15","arxiv_id":"1603.04779","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/revisiting-batch-normalization-for-practical#ran","syntology_url":"https://syntology.ai/paper/1603.04779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.04779"}},"official":null}},{"url":"/paper/seq-nms-for-video-object-detection","slug":"seq-nms-for-video-object-detection","title":"Seq-NMS for Video Object Detection","date":"2016-02-26","arxiv_id":"1602.08465","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/seq-nms-for-video-object-detection#ran","syntology_url":"https://syntology.ai/paper/1602.08465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.08465"}},"official":null}},{"url":"/paper/relief-r-cnn-utilizing-convolutional-features","slug":"relief-r-cnn-utilizing-convolutional-features","title":"Relief R-CNN : Utilizing Convolutional Features for Fast Object Detection","date":"2016-01-25","arxiv_id":"1601.06719","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-object-detection-using-adjacency-and","slug":"adaptive-object-detection-using-adjacency-and","title":"Adaptive Object Detection Using Adjacency and Zoom Prediction","date":"2015-12-24","arxiv_id":"1512.07711","repositories_listed":1,"syntology":null},{"url":"/paper/object-detection-via-a-multi-region-and","slug":"object-detection-via-a-multi-region-and","title":"Object Detection via a Multi-Region and Semantic Segmentation-Aware CNN Model","date":"2015-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-tube-extraction-using","slug":"unsupervised-tube-extraction-using","title":"Unsupervised Tube Extraction Using Transductive Learning and Dense Trajectories","date":"2015-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/densecap-fully-convolutional-localization","slug":"densecap-fully-convolutional-localization","title":"DenseCap: Fully Convolutional Localization Networks for Dense Captioning","date":"2015-11-24","arxiv_id":"1511.07571","repositories_listed":1,"syntology":null},{"url":"/paper/locnet-improving-localization-accuracy-for","slug":"locnet-improving-localization-accuracy-for","title":"LocNet: Improving Localization Accuracy for Object Detection","date":"2015-11-24","arxiv_id":"1511.07763","repositories_listed":1,"syntology":null},{"url":"/paper/training-deep-neural-networks-via-direct-loss","slug":"training-deep-neural-networks-via-direct-loss","title":"Training Deep Neural Networks via Direct Loss Minimization","date":"2015-11-19","arxiv_id":"1511.06411","repositories_listed":1,"syntology":null},{"url":"/paper/deep-convolutional-neural-networks-for-4","slug":"deep-convolutional-neural-networks-for-4","title":"Deep convolutional neural networks for pedestrian detection","date":"2015-10-13","arxiv_id":"1510.03608","repositories_listed":1,"syntology":null},{"url":"/paper/background-image-generation-using-boolean","slug":"background-image-generation-using-boolean","title":"Background Image Generation Using Boolean Operations","date":"2015-10-04","arxiv_id":"1510.00889","repositories_listed":1,"syntology":null},{"url":"/paper/libhog-energy-efficient-histogram-of-oriented","slug":"libhog-energy-efficient-histogram-of-oriented","title":"libHOG: Energy-Efficient Histogram of Oriented Gradient Computation","date":"2015-09-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/stc-a-simple-to-complex-framework-for-weakly","slug":"stc-a-simple-to-complex-framework-for-weakly","title":"STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation","date":"2015-09-10","arxiv_id":"1509.03150","repositories_listed":1,"syntology":null},{"url":"/paper/lcnn-low-level-feature-embedded-cnn-for","slug":"lcnn-low-level-feature-embedded-cnn-for","title":"LCNN: Low-level Feature Embedded CNN for Salient Object Detection","date":"2015-08-17","arxiv_id":"1508.03928","repositories_listed":1,"syntology":null},{"url":"/paper/convolutional-color-constancy","slug":"convolutional-color-constancy","title":"Convolutional Color Constancy","date":"2015-07-02","arxiv_id":"1507.00410","repositories_listed":1,"syntology":null},{"url":"/paper/robust-optimization-for-deep-regression","slug":"robust-optimization-for-deep-regression","title":"Robust Optimization for Deep Regression","date":"2015-05-25","arxiv_id":"1505.06606","repositories_listed":1,"syntology":null},{"url":"/paper/object-proposal-evaluation-protocol-is","slug":"object-proposal-evaluation-protocol-is","title":"Object-Proposal Evaluation Protocol is 'Gameable'","date":"2015-05-21","arxiv_id":"1505.05836","repositories_listed":1,"syntology":null},{"url":"/paper/object-detection-via-a-multi-region-semantic","slug":"object-detection-via-a-multi-region-semantic","title":"Object detection via a multi-region & semantic segmentation-aware CNN model","date":"2015-05-07","arxiv_id":"1505.01749","repositories_listed":1,"syntology":null},{"url":"/paper/visualizing-object-detection-features","slug":"visualizing-object-detection-features","title":"Visualizing Object Detection Features","date":"2015-02-19","arxiv_id":"1502.05461","repositories_listed":1,"syntology":null},{"url":"/paper/analysing-domain-shift-factors-between-videos","slug":"analysing-domain-shift-factors-between-videos","title":"Analysing domain shift factors between videos and images for object detection","date":"2015-01-06","arxiv_id":"1501.01186","repositories_listed":1,"syntology":null},{"url":"/paper/finding-action-tubes","slug":"finding-action-tubes","title":"Finding Action Tubes","date":"2014-11-21","arxiv_id":"1411.6031","repositories_listed":1,"syntology":null},{"url":"/paper/deformable-part-models-are-convolutional","slug":"deformable-part-models-are-convolutional","title":"Deformable Part Models are Convolutional Neural Networks","date":"2014-09-18","arxiv_id":"1409.5403","repositories_listed":1,"syntology":null},{"url":"/paper/object-detection-through-exploration-with-a","slug":"object-detection-through-exploration-with-a","title":"Object Detection Through Exploration With A Foveated Visual Field","date":"2014-08-04","arxiv_id":"1408.0814","repositories_listed":1,"syntology":null},{"url":"/paper/learning-rich-features-from-rgb-d-images-for","slug":"learning-rich-features-from-rgb-d-images-for","title":"Learning Rich Features from RGB-D Images for Object Detection and Segmentation","date":"2014-07-22","arxiv_id":"1407.5736","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-rich-features-from-rgb-d-images-for#ran","syntology_url":"https://syntology.ai/paper/1407.5736","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1407.5736"}},"official":null}},{"url":"/paper/lsda-large-scale-detection-through-adaptation","slug":"lsda-large-scale-detection-through-adaptation","title":"LSDA: Large Scale Detection Through Adaptation","date":"2014-07-18","arxiv_id":"1407.5035","repositories_listed":1,"syntology":null},{"url":"/paper/how-good-are-detection-proposals-really","slug":"how-good-are-detection-proposals-really","title":"How good are detection proposals, really?","date":"2014-06-26","arxiv_id":"1406.6962","repositories_listed":1,"syntology":null},{"url":"/paper/return-of-the-devil-in-the-details-delving","slug":"return-of-the-devil-in-the-details-delving","title":"Return of the Devil in the Details: Delving Deep into Convolutional Nets","date":"2014-05-14","arxiv_id":"1405.3531","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-nested-sampling-an-efficient-and","slug":"multimodal-nested-sampling-an-efficient-and","title":"Multimodal nested sampling: an efficient and robust alternative to MCMC methods for astronomical data analysis","date":"2007-04-27","arxiv_id":"0704.3704","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multimodal-nested-sampling-an-efficient-and#ran","syntology_url":"https://syntology.ai/paper/0704.3704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"0704.3704"}},"official":null}},{"url":null,"slug":"a-real-time-system-for-egocentric-hand-object","title":"A Real-Time System for Egocentric Hand-Object Interaction Detection in Industrial Domains","date":"2025-07-17","arxiv_id":"2507.13326","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoupled-prob-decoupled-query-initialization","title":"Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection","date":"2025-07-17","arxiv_id":"2507.13085","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-lidar-based-traffic-movement-count","title":"Dual LiDAR-Based Traffic Movement Count Estimation at a Signalized Intersection: Deployment, Data Collection, and Preliminary Analysis","date":"2025-07-17","arxiv_id":"2507.13073","repositories_listed":0,"syntology":null},{"url":null,"slug":"rs-tinynet-stage-wise-feature-fusion-network","title":"RS-TinyNet: Stage-wise Feature Fusion Network for Detecting Tiny Objects in Remote Sensing Images","date":"2025-07-17","arxiv_id":"2507.13120","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-based-perception-for-autonomous","title":"Vision-based Perception for Autonomous Vehicles in Obstacle Avoidance Scenarios","date":"2025-07-16","arxiv_id":"2507.12449","repositories_listed":0,"syntology":null},{"url":null,"slug":"tomato-multi-angle-multi-pose-dataset-for","title":"Tomato Multi-Angle Multi-Pose Dataset for Fine-Grained Phenotyping","date":"2025-07-15","arxiv_id":"2507.11279","repositories_listed":0,"syntology":null},{"url":null,"slug":"ecore-energy-conscious-optimized-routing-for","title":"ECORE: Energy-Conscious Optimized Routing for Deep Learning Models at the Edge","date":"2025-07-08","arxiv_id":"2507.06011","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-of-rail-line-track-and-human-beings","title":"Detection of Rail Line Track and Human Beings Near the Track to Avoid Accidents","date":"2025-07-03","arxiv_id":"2507.03040","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-dataset-for-underground-miner","title":"A Comprehensive Dataset for Underground Miner Detection in Diverse Scenario","date":"2025-06-26","arxiv_id":"2506.21451","repositories_listed":0,"syntology":null},{"url":null,"slug":"duet-dual-incremental-object-detection-via","title":"DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic","date":"2025-06-26","arxiv_id":"2506.21260","repositories_listed":0,"syntology":null},{"url":null,"slug":"thermaldiffusion-visual-to-thermal-image-to","title":"ThermalDiffusion: Visual-to-Thermal Image-to-Image Translation for Autonomous Navigation","date":"2025-06-26","arxiv_id":"2506.20969","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-hallucination-for-self-supervised","title":"Feature Hallucination for Self-supervised Action Recognition","date":"2025-06-25","arxiv_id":"2506.20342","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-codicology-to-code-a-comparative-study","title":"From Codicology to Code: A Comparative Study of Transformer and YOLO-based Detectors for Layout Analysis in Historical Documents","date":"2025-06-25","arxiv_id":"2506.20326","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-multi-frame-integration-for","title":"Lightweight Multi-Frame Integration for Robust YOLO Object Detection in Videos","date":"2025-06-25","arxiv_id":"2506.20550","repositories_listed":0,"syntology":null},{"url":null,"slug":"tdir-transformer-based-diffusion-for-image","title":"TDiR: Transformer based Diffusion for Image Restoration Tasks","date":"2025-06-25","arxiv_id":"2506.20302","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-multi-sensor-fusion-perception","title":"A Survey of Multi-sensor Fusion Perception for Embodied AI: Background, Methods, Challenges and Prospects","date":"2025-06-24","arxiv_id":"2506.19769","repositories_listed":0,"syntology":null},{"url":null,"slug":"unfolding-the-past-a-comprehensive-deep","title":"Unfolding the Past: A Comprehensive Deep Learning Approach to Analyzing Incunabula Pages","date":"2025-06-22","arxiv_id":"2506.18069","repositories_listed":0,"syntology":null},{"url":null,"slug":"class-agnostic-instance-level-descriptor-for","title":"Class Agnostic Instance-level Descriptor for Visual Instance Search","date":"2025-06-20","arxiv_id":"2506.16745","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrospective-memory-for-camouflaged-object","title":"Retrospective Memory for Camouflaged Object Detection","date":"2025-06-18","arxiv_id":"2506.15244","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-of-two-methods-for-stationary","title":"Comparison of Two Methods for Stationary Incident Detection Based on Background Image","date":"2025-06-17","arxiv_id":"2506.14256","repositories_listed":0,"syntology":null},{"url":null,"slug":"findmeifyoucan-bringing-open-set-metrics-to","title":"FindMeIfYouCan: Bringing Open Set metrics to $\\textit{near} $, $ \\textit{far} $ and $\\textit{farther}$ Out-of-Distribution Object Detection","date":"2025-06-16","arxiv_id":"2506.14008","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-real-is-carlas-dynamic-vision-sensor-a","title":"How Real is CARLAs Dynamic Vision Sensor? A Study on the Sim-to-Real Gap in Traffic Object Detection","date":"2025-06-16","arxiv_id":"2506.13722","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparse-convolutional-recurrent-learning-for","title":"Sparse Convolutional Recurrent Learning for Efficient Event-based Neuromorphic Object Detection","date":"2025-06-16","arxiv_id":"2506.13440","repositories_listed":0,"syntology":null},{"url":null,"slug":"uav-object-detection-and-positioning-in-a","title":"UAV Object Detection and Positioning in a Mining Industrial Metaverse with Custom Geo-Referenced Data","date":"2025-06-16","arxiv_id":"2506.13505","repositories_listed":0,"syntology":null},{"url":null,"slug":"teleoperated-driving-a-new-challenge-for-3d","title":"Teleoperated Driving: a New Challenge for 3D Object Detection in Compressed Point Clouds","date":"2025-06-13","arxiv_id":"2506.11804","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-based-lifting-of-2d-object-detections","title":"Vision-based Lifting of 2D Object Detections for Automated Driving","date":"2025-06-13","arxiv_id":"2506.11839","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-medical-visual-representation","title":"Improving Medical Visual Representation Learning with Pathological-level Cross-Modal Alignment and Correlation Exploration","date":"2025-06-12","arxiv_id":"2506.10573","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-masked-bernoulli-diffusion-for","title":"Uncertainty-Masked Bernoulli Diffusion for Camouflaged Object Detection Refinement","date":"2025-06-12","arxiv_id":"2506.10712","repositories_listed":0,"syntology":null},{"url":null,"slug":"cem-fbgtinydet-context-enhanced-foreground","title":"CEM-FBGTinyDet: Context-Enhanced Foreground Balance with Gradient Tuning for tiny Objects","date":"2025-06-11","arxiv_id":"2506.09897","repositories_listed":0,"syntology":null},{"url":null,"slug":"dyss-dynamic-queries-and-state-space-learning","title":"DySS: Dynamic Queries and State-Space Learning for Efficient 3D Object Detection from Multi-Camera Videos","date":"2025-06-11","arxiv_id":"2506.10242","repositories_listed":0,"syntology":null},{"url":null,"slug":"adam-autonomous-discovery-and-annotation","title":"ADAM: Autonomous Discovery and Annotation Model using LLMs for Context-Aware Annotations","date":"2025-06-10","arxiv_id":"2506.08968","repositories_listed":0,"syntology":null},{"url":null,"slug":"atas-any-to-any-self-distillation-for","title":"ATAS: Any-to-Any Self-Distillation for Enhanced Open-Vocabulary Dense Prediction","date":"2025-06-10","arxiv_id":"2506.08678","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-augmentation-for-small-object-using-fast","title":"Data Augmentation For Small Object using Fast AutoAugment","date":"2025-06-10","arxiv_id":"2506.08956","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-neural-collapse-detection","title":"Hierarchical Neural Collapse Detection Transformer for Class Incremental Object Detection","date":"2025-06-10","arxiv_id":"2506.08562","repositories_listed":0,"syntology":null},{"url":null,"slug":"wd-detr-wavelet-denoising-enhanced-real-time","title":"WD-DETR: Wavelet Denoising-Enhanced Real-Time Object Detection Transformer for Robot Perception with Event Cameras","date":"2025-06-10","arxiv_id":"2506.09098","repositories_listed":0,"syntology":null},{"url":null,"slug":"crosswalknet-an-optimized-deep-learning","title":"CrosswalkNet: An Optimized Deep Learning Framework for Pedestrian Crosswalk Detection in Aerial Images with High-Performance Computing","date":"2025-06-09","arxiv_id":"2506.07885","repositories_listed":0,"syntology":null},{"url":null,"slug":"sam2auto-auto-annotation-using-flash","title":"SAM2Auto: Auto Annotation Using FLASH","date":"2025-06-09","arxiv_id":"2506.07850","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatiallm-training-large-language-models-for","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","date":"2025-06-09","arxiv_id":"2506.07491","repositories_listed":0,"syntology":null},{"url":null,"slug":"spikesmoke-spiking-neural-networks-for","title":"SpikeSMOKE: Spiking Neural Networks for Monocular 3D Object Detection with Cross-Scale Gated Coding","date":"2025-06-09","arxiv_id":"2506.07737","repositories_listed":0,"syntology":null},{"url":null,"slug":"token-transforming-a-unified-and-training","title":"Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration","date":"2025-06-06","arxiv_id":"2506.05709","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-annotation-gaps-transferring-labels","title":"Bridging Annotation Gaps: Transferring Labels to Align Object Detection Datasets","date":"2025-06-05","arxiv_id":"2506.04737","repositories_listed":0,"syntology":null},{"url":null,"slug":"gen-n-val-agentic-image-data-generation-and","title":"Gen-n-Val: Agentic Image Data Generation and Validation","date":"2025-06-05","arxiv_id":"2506.04676","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-dataset-generation-for-autonomous","title":"Synthetic Dataset Generation for Autonomous Mobile Robots Using 3D Gaussian Splatting for Vision Training","date":"2025-06-05","arxiv_id":"2506.05092","repositories_listed":0,"syntology":null}],"record_sha256":"9744af54191ded7cefdab8c2325b95c6b10549c3b0bd1eb21f417cecd28b92fb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}