{"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-recognition/papers/7","list_of":"/task/object-recognition","task":"Object Recognition","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":7,"pages_in_order":21,"rows_per_page":100,"rows":[601,700],"of":2042,"counts":{"archive_papers_tagged":2042,"with_a_code_link":577,"where_syntology_ran_a_sample":132,"not_listed_spam_title":0,"listed":2042,"listed_where_code_ran":132,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":100,"every_run_a_failure_of_syntologys_instrument":32,"listed_with_a_run_with_no_instrument_failure":100,"listed_every_run_a_failure_of_syntologys_instrument":32,"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-recognition","prev":"/task/object-recognition/papers/6","next":"/task/object-recognition/papers/8","papers":[{"url":null,"slug":"beyond-recognition-evaluating-visual","title":"Beyond Recognition: Evaluating Visual Perspective Taking in Vision Language Models","date":"2025-05-03","arxiv_id":"2505.03821","repositories_listed":0,"syntology":null},{"url":null,"slug":"transferable-adversarial-attacks-on-black-box","title":"Transferable Adversarial Attacks on Black-Box Vision-Language Models","date":"2025-05-02","arxiv_id":"2505.01050","repositories_listed":0,"syntology":null},{"url":null,"slug":"zoomer-adaptive-image-focus-optimization-for","title":"Zoomer: Adaptive Image Focus Optimization for Black-box MLLM","date":"2025-04-30","arxiv_id":"2505.00742","repositories_listed":0,"syntology":null},{"url":null,"slug":"lm-mcvt-a-lightweight-multi-modal-multi-view","title":"LM-MCVT: A Lightweight Multi-modal Multi-view Convolutional-Vision Transformer Approach for 3D Object Recognition","date":"2025-04-27","arxiv_id":"2504.19256","repositories_listed":0,"syntology":null},{"url":null,"slug":"disaggregated-deep-learning-via-in-physics","title":"Disaggregated Deep Learning via In-Physics Computing at Radio Frequency","date":"2025-04-24","arxiv_id":"2504.17752","repositories_listed":0,"syntology":null},{"url":null,"slug":"v-2-r-bench-holistically-evaluating-lvlm","title":"V$^2$R-Bench: Holistically Evaluating LVLM Robustness to Fundamental Visual Variations","date":"2025-04-23","arxiv_id":"2504.16727","repositories_listed":0,"syntology":null},{"url":"/paper/quantum-doubly-stochastic-transformers","slug":"quantum-doubly-stochastic-transformers","title":"Quantum Doubly Stochastic Transformers","date":"2025-04-22","arxiv_id":"2504.16275","repositories_listed":0,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"3 ran (of which 2 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) · 1 unverified","sample_list":"/paper/quantum-doubly-stochastic-transformers#ran","syntology_url":"https://syntology.ai/paper/2504.16275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.16275"}},"official":null}},{"url":null,"slug":"dvlta-vqa-decoupled-vision-language-modeling","title":"DVLTA-VQA: Decoupled Vision-Language Modeling with Text-Guided Adaptation for Blind Video Quality Assessment","date":"2025-04-16","arxiv_id":"2504.11733","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-language-models-show-widespread-visual","title":"Visual Language Models show widespread visual deficits on neuropsychological tests","date":"2025-04-15","arxiv_id":"2504.10786","repositories_listed":0,"syntology":null},{"url":null,"slug":"hardware-algorithms-and-applications-of-the","title":"Hardware, Algorithms, and Applications of the Neuromorphic Vision Sensor: a Review","date":"2025-04-11","arxiv_id":"2504.08588","repositories_listed":0,"syntology":null},{"url":null,"slug":"d-feat-occlusions-diffusion-features-for","title":"D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognition","date":"2025-04-08","arxiv_id":"2504.06432","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-egocentric-video-question-answering","title":"Advancing Egocentric Video Question Answering with Multimodal Large Language Models","date":"2025-04-06","arxiv_id":"2504.04550","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-multimodal-language-models-as","title":"Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users","date":"2025-03-28","arxiv_id":"2503.22610","repositories_listed":0,"syntology":null},{"url":null,"slug":"forcepose-a-deep-learning-approach-for-force","title":"ForcePose: A Deep Learning Approach for Force Calculation Based on Action Recognition Using MediaPipe Pose Estimation Combined with Object Detection","date":"2025-03-28","arxiv_id":"2503.22363","repositories_listed":0,"syntology":null},{"url":null,"slug":"ducksegmentation-a-segmentation-model-based","title":"DuckSegmentation: A segmentation model based on the AnYue Hemp Duck Dataset","date":"2025-03-27","arxiv_id":"2503.21323","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-3d-geometric-priors-in-2d-rotation","title":"Leveraging 3D Geometric Priors in 2D Rotation Symmetry Detection","date":"2025-03-26","arxiv_id":"2503.20235","repositories_listed":0,"syntology":null},{"url":null,"slug":"matt-gs-masked-attention-based-3dgs-for-robot","title":"MATT-GS: Masked Attention-based 3DGS for Robot Perception and Object Detection","date":"2025-03-25","arxiv_id":"2503.19330","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-the-road-ahead-a-knowledge-graph","title":"Predicting the Road Ahead: A Knowledge Graph based Foundation Model for Scene Understanding in Autonomous Driving","date":"2025-03-24","arxiv_id":"2503.18730","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-semantics-rediscovering-spatial","title":"Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models","date":"2025-03-21","arxiv_id":"2503.17349","repositories_listed":0,"syntology":null},{"url":null,"slug":"tulip-towards-unified-language-image","title":"TULIP: Towards Unified Language-Image Pretraining","date":"2025-03-19","arxiv_id":"2503.15485","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmenting-image-annotation-a-human-lmm","title":"Augmenting Image Annotation: A Human-LMM Collaborative Framework for Efficient Object Selection and Label Generation","date":"2025-03-14","arxiv_id":"2503.11096","repositories_listed":0,"syntology":null},{"url":null,"slug":"osma-bench-evaluating-open-semantic-mapping","title":"OSMa-Bench: Evaluating Open Semantic Mapping Under Varying Lighting Conditions","date":"2025-03-13","arxiv_id":"2503.10331","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-what-s-not-there-spurious-correlation","title":"Seeing What's Not There: Spurious Correlation in Multimodal LLMs","date":"2025-03-11","arxiv_id":"2503.08884","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-centric-world-model-for-language","title":"Object-Centric World Model for Language-Guided Manipulation","date":"2025-03-08","arxiv_id":"2503.06170","repositories_listed":0,"syntology":null},{"url":null,"slug":"afford-x-generalizable-and-slim-affordance","title":"Afford-X: Generalizable and Slim Affordance Reasoning for Task-oriented Manipulation","date":"2025-03-05","arxiv_id":"2503.03556","repositories_listed":0,"syntology":null},{"url":null,"slug":"identity-documents-recognition-and-detection","title":"Identity documents recognition and detection using semantic segmentation with convolutional neural network","date":"2025-03-03","arxiv_id":"2503.01085","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-infrared-small-object","title":"Deep learning based infrared small object segmentation: Challenges and future directions","date":"2025-02-20","arxiv_id":"2502.14168","repositories_listed":0,"syntology":null},{"url":null,"slug":"raptor-refined-approach-for-product-table","title":"RAPTOR: Refined Approach for Product Table Object Recognition","date":"2025-02-19","arxiv_id":"2502.14918","repositories_listed":0,"syntology":null},{"url":null,"slug":"revealing-bias-formation-in-deep-neural","title":"Revealing Bias Formation in Deep Neural Networks Through the Geometric Mechanisms of Human Visual Decoupling","date":"2025-02-17","arxiv_id":"2502.11809","repositories_listed":0,"syntology":null},{"url":null,"slug":"see-the-world-discover-knowledge-a-chinese","title":"\"See the World, Discover Knowledge\": A Chinese Factuality Evaluation for Large Vision Language Models","date":"2025-02-17","arxiv_id":"2502.11718","repositories_listed":0,"syntology":null},{"url":null,"slug":"occlusion-aware-text-image-point-cloud","title":"Occlusion-aware Text-Image-Point Cloud Pretraining for Open-World 3D Object Recognition","date":"2025-02-15","arxiv_id":"2502.10674","repositories_listed":0,"syntology":null},{"url":null,"slug":"dcenwcnet-a-deep-cnn-ensemble-network-for","title":"DCENWCNet: A Deep CNN Ensemble Network for White Blood Cell Classification with LIME-Based Explainability","date":"2025-02-08","arxiv_id":"2502.05459","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-the-potential-of-imarkers-invisible","title":"Unveiling the Potential of iMarkers: Invisible Fiducial Markers for Advanced Robotics","date":"2025-01-26","arxiv_id":"2501.15505","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-hallucination-in-large-vision","title":"Evaluating Hallucination in Large Vision-Language Models based on Context-Aware Object Similarities","date":"2025-01-25","arxiv_id":"2501.15046","repositories_listed":0,"syntology":null},{"url":null,"slug":"development-of-an-inclusive-educational","title":"Development of an Inclusive Educational Platform Using Open Technologies and Machine Learning: A Case Study on Accessibility Enhancement","date":"2025-01-22","arxiv_id":"2503.15501","repositories_listed":0,"syntology":null},{"url":null,"slug":"rl-rc-dot-a-block-level-rl-agent-for-task","title":"RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression","date":"2025-01-21","arxiv_id":"2501.12216","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-powered-assistive-technologies-for-visual","title":"AI-Powered Assistive Technologies for Visual Impairment","date":"2025-01-14","arxiv_id":"2503.15494","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-zero-shot-explainable-video","title":"Towards Zero-Shot & Explainable Video Description by Reasoning over Graphs of Events in Space and Time","date":"2025-01-14","arxiv_id":"2501.08460","repositories_listed":0,"syntology":null},{"url":null,"slug":"guided-sam-label-efficient-part-segmentation","title":"Guided SAM: Label-Efficient Part Segmentation","date":"2025-01-13","arxiv_id":"2501.07434","repositories_listed":0,"syntology":null},{"url":null,"slug":"perceptual-inductive-bias-is-what-you-need","title":"Perceptual Inductive Bias Is What You Need Before Contrastive Learning","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial457-a-diagnostic-benchmark-for-6d","title":"Spatial457: A Diagnostic Benchmark for 6D Spatial Reasoning of Large Mutimodal Models","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-multimodal-rag-llm-for-accurate","title":"Enhanced Multimodal RAG-LLM for Accurate Visual Question Answering","date":"2024-12-30","arxiv_id":"2412.20927","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-based-wearable-vision-assistance-system","title":"AI-based Wearable Vision Assistance System for the Visually Impaired: Integrating Real-Time Object Recognition and Contextual Understanding Using Large Vision-Language Models","date":"2024-12-28","arxiv_id":"2412.20059","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-same-but-different-impact-of-animal","title":"The same but different: impact of animal facility sanitary status on a transgenic mouse model of Alzheimer's disease","date":"2024-12-24","arxiv_id":"2412.18258","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-classification-by-description-extending","title":"Real Classification by Description: Extending CLIP's Limits of Part Attributes Recognition","date":"2024-12-18","arxiv_id":"2412.13947","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-oriented-object-detection-with","title":"Efficient Oriented Object Detection with Enhanced Small Object Recognition in Aerial Images","date":"2024-12-17","arxiv_id":"2412.12562","repositories_listed":0,"syntology":null},{"url":null,"slug":"cognav-cognitive-process-modeling-for-object","title":"CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMs","date":"2024-12-11","arxiv_id":"2412.10439","repositories_listed":0,"syntology":null},{"url":null,"slug":"proactive-adversarial-defense-harnessing","title":"Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images","date":"2024-12-11","arxiv_id":"2412.08755","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-3d-object-detection-in-autonomous","title":"Enhancing 3D Object Detection in Autonomous Vehicles Based on Synthetic Virtual Environment Analysis","date":"2024-12-10","arxiv_id":"2412.07509","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-foundation-models-actively-gather","title":"Can foundation models actively gather information in interactive environments to test hypotheses?","date":"2024-12-09","arxiv_id":"2412.06438","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimized-cnns-for-rapid-3d-point-cloud","title":"Optimized CNNs for Rapid 3D Point Cloud Object Recognition","date":"2024-12-03","arxiv_id":"2412.02855","repositories_listed":0,"syntology":null},{"url":null,"slug":"textured-as-is-bim-via-gis-informed-point","title":"Textured As-Is BIM via GIS-informed Point Cloud Segmentation","date":"2024-11-28","arxiv_id":"2411.18898","repositories_listed":0,"syntology":null},{"url":null,"slug":"nemo-can-multimodal-llms-identify-attribute","title":"NEMO: Can Multimodal LLMs Identify Attribute-Modified Objects?","date":"2024-11-26","arxiv_id":"2411.17794","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-photorealism-in-game-engines-for","title":"Comparing Photorealism in Game Engines for Synthetic Maritime Computer Vision Datasets","date":"2024-11-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-open-vocabulary-object","title":"Fine-Grained Open-Vocabulary Object Recognition via User-Guided Segmentation","date":"2024-11-23","arxiv_id":"2411.15620","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightffdnets-lightweight-convolutional-neural","title":"LightFFDNets: Lightweight Convolutional Neural Networks for Rapid Facial Forgery Detection","date":"2024-11-18","arxiv_id":"2411.11826","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-tailed-object-detection-pre-training","title":"Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction","date":"2024-11-14","arxiv_id":"2411.09453","repositories_listed":0,"syntology":null},{"url":null,"slug":"dipme-haptic-recognition-of-granular-media","title":"DipMe: Haptic Recognition of Granular Media for Tangible Interactive Applications","date":"2024-11-13","arxiv_id":"2411.08641","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-recognition-in-human-computer","title":"Object Recognition in Human Computer Interaction:- A Comparative Analysis","date":"2024-11-06","arxiv_id":"2411.04263","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-gaze-behavior-boosts-self-supervised","title":"Active Gaze Behavior Boosts Self-Supervised Object Learning","date":"2024-11-04","arxiv_id":"2411.01969","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-object-discovery-a-comprehensive","title":"Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy","date":"2024-10-30","arxiv_id":"2411.00868","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-the-untrainable-introducing","title":"Training the Untrainable: Introducing Inductive Bias via Representational Alignment","date":"2024-10-26","arxiv_id":"2410.20035","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-target-driven-instance-detection","title":"Few-shot target-driven instance detection based on open-vocabulary object detection models","date":"2024-10-21","arxiv_id":"2410.16028","repositories_listed":0,"syntology":null},{"url":null,"slug":"development-of-image-collection-method-using","title":"Development of Image Collection Method Using YOLO and Siamese Network","date":"2024-10-16","arxiv_id":"2410.12561","repositories_listed":0,"syntology":null},{"url":null,"slug":"big-little-vision-transformer-for-efficient","title":"big.LITTLE Vision Transformer for Efficient Visual Recognition","date":"2024-10-14","arxiv_id":"2410.10267","repositories_listed":0,"syntology":null},{"url":null,"slug":"chartkg-a-knowledge-graph-based","title":"ChartKG: A Knowledge-Graph-Based Representation for Chart Images","date":"2024-10-13","arxiv_id":"2410.09761","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-free-open-ended-object-detection-and","title":"Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts","date":"2024-10-08","arxiv_id":"2410.05963","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-object-detection-with-a-machine-learning","title":"Fast Object Detection with a Machine Learning Edge Device","date":"2024-10-05","arxiv_id":"2410.04173","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-we-remove-the-ground-obstacle-aware-point","title":"Can We Remove the Ground? Obstacle-aware Point Cloud Compression for Remote Object Detection","date":"2024-10-01","arxiv_id":"2410.00582","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-segmentation-of-unmanned-aerial","title":"Semantic Segmentation of Unmanned Aerial Vehicle Remote Sensing Images using SegFormer","date":"2024-10-01","arxiv_id":"2410.01092","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-crime-scene-investigations-through","title":"Enhancing Crime Scene Investigations through Virtual Reality and Deep Learning Techniques","date":"2024-09-27","arxiv_id":"2409.18458","repositories_listed":0,"syntology":null},{"url":null,"slug":"you-only-speak-once-to-see","title":"You Only Speak Once to See","date":"2024-09-27","arxiv_id":"2409.18372","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-powered-augmented-reality-for-satellite","title":"AI-Powered Augmented Reality for Satellite Assembly, Integration and Test","date":"2024-09-26","arxiv_id":"2409.18101","repositories_listed":0,"syntology":null},{"url":null,"slug":"formula-supervised-visual-geometric-pre","title":"Formula-Supervised Visual-Geometric Pre-training","date":"2024-09-20","arxiv_id":"2409.13535","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dynamic-vision-sensor-object-recognition","title":"A dynamic vision sensor object recognition model based on trainable event-driven convolution and spiking attention mechanism","date":"2024-09-19","arxiv_id":"2409.12691","repositories_listed":0,"syntology":null},{"url":null,"slug":"eventdance-language-guided-unsupervised","title":"EventDance++: Language-guided Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognition","date":"2024-09-19","arxiv_id":"2409.12778","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-vlms-reasoning-about-persuasive","title":"Benchmarking VLMs' Reasoning About Persuasive Atypical Images","date":"2024-09-16","arxiv_id":"2409.10719","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalization-boosted-adapter-for-open","title":"Generalization Boosted Adapter for Open-Vocabulary Segmentation","date":"2024-09-13","arxiv_id":"2409.08468","repositories_listed":0,"syntology":null},{"url":null,"slug":"performance-assessment-of-feature-detection","title":"Performance Assessment of Feature Detection Methods for 2-D FS Sonar Imagery","date":"2024-09-11","arxiv_id":"2409.07004","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-bayesian-framework-for-active-object","title":"A Bayesian Framework for Active Tactile Object Recognition, Pose Estimation and Shape Transfer Learning","date":"2024-09-10","arxiv_id":"2409.06912","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-deep-predictive-coding-networks-for","title":"Fast Deep Predictive Coding Networks for Videos Feature Extraction without Labels","date":"2024-09-08","arxiv_id":"2409.04945","repositories_listed":0,"syntology":null},{"url":null,"slug":"limited-but-consistent-gains-in-adversarial","title":"Limited but consistent gains in adversarial robustness by co-training object recognition models with human EEG","date":"2024-09-05","arxiv_id":"2409.03646","repositories_listed":0,"syntology":null},{"url":null,"slug":"uav-unmanned-aerial-vehicles-diverse","title":"UAV (Unmanned Aerial Vehicles): Diverse Applications of UAV Datasets in Segmentation, Classification, Detection, and Tracking","date":"2024-09-05","arxiv_id":"2409.03245","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resolution-object-recognition-with-cross","title":"Low-Resolution Object Recognition with Cross-Resolution Relational Contrastive Distillation","date":"2024-09-04","arxiv_id":"2409.02555","repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminative-spatial-semantic-vos-solution","title":"Discriminative Spatial-Semantic VOS Solution: 1st Place Solution for 6th LSVOS","date":"2024-08-29","arxiv_id":"2408.16431","repositories_listed":0,"syntology":null},{"url":null,"slug":"finding-closure-a-closer-look-at-the-gestalt","title":"Finding Closure: A Closer Look at the Gestalt Law of Closure in Convolutional Neural Networks","date":"2024-08-22","arxiv_id":"2408.12460","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-small-is-big-enough-open-labeled-datasets","title":"How Small is Big Enough? Open Labeled Datasets and the Development of Deep Learning","date":"2024-08-19","arxiv_id":"2408.10359","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-domain-generalization-for-multi-modal","title":"Robust Domain Generalization for Multi-modal Object Recognition","date":"2024-08-11","arxiv_id":"2408.05831","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-how-blind-users-handle-object","title":"Understanding How Blind Users Handle Object Recognition Errors: Strategies and Challenges","date":"2024-08-06","arxiv_id":"2408.03303","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02209","title":"Source-Free Domain-Invariant Performance Prediction","date":"2024-08-05","arxiv_id":"2408.02209","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01712","title":"A General Ambiguity Model for Binary Edge Images with Edge Tracing and its Implementation","date":"2024-08-03","arxiv_id":"2408.01712","repositories_listed":0,"syntology":null},{"url":null,"slug":"ezsr-event-based-zero-shot-recognition","title":"EZSR: Event-based Zero-Shot Recognition","date":"2024-07-31","arxiv_id":"2407.21616","repositories_listed":0,"syntology":null},{"url":null,"slug":"combined-cnn-and-vit-features-off-the-shelf","title":"Combined CNN and ViT features off-the-shelf: Another astounding baseline for recognition","date":"2024-07-28","arxiv_id":"2407.19472","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-based-density-recognition","title":"AI-based Density Recognition","date":"2024-07-24","arxiv_id":"2407.17064","repositories_listed":0,"syntology":null},{"url":null,"slug":"affordance-labeling-and-exploration-a","title":"Affordance Labeling and Exploration: A Manifold-Based Approach","date":"2024-07-22","arxiv_id":"2407.15479","repositories_listed":0,"syntology":null},{"url":null,"slug":"emocam-toward-understanding-what-drives-cnn","title":"EmoCAM: Toward Understanding What Drives CNN-based Emotion Recognition","date":"2024-07-19","arxiv_id":"2407.14314","repositories_listed":0,"syntology":null},{"url":null,"slug":"octrack-benchmarking-the-open-corpus-multi","title":"OCTrack: Benchmarking the Open-Corpus Multi-Object Tracking","date":"2024-07-19","arxiv_id":"2407.14047","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-3d-occupancy-prediction-via","title":"Real-Time 3D Occupancy Prediction via Geometric-Semantic Disentanglement","date":"2024-07-18","arxiv_id":"2407.13155","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-verification-of-dnns-for-object","title":"Data-driven Verification of DNNs for Object Recognition","date":"2024-07-17","arxiv_id":"2408.00783","repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-cornet-human-fmri-representations","title":"Teaching CORnet Human fMRI Representations for Enhanced Model-Brain Alignment","date":"2024-07-15","arxiv_id":"2407.10414","repositories_listed":0,"syntology":null}],"record_sha256":"56c5a6a3c9ec4064196b4c3ffca7997fb520b1d8a7a38bd2281a59055d23c970","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}