{"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/visual-reasoning/papers/7","list_of":"/task/visual-reasoning","task":"Visual Reasoning","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":7,"rows_per_page":100,"rows":[601,698],"of":698,"counts":{"archive_papers_tagged":698,"with_a_code_link":356,"where_syntology_ran_a_sample":165,"not_listed_spam_title":0,"listed":698,"listed_where_code_ran":165,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":130,"every_run_a_failure_of_syntologys_instrument":35,"listed_with_a_run_with_no_instrument_failure":130,"listed_every_run_a_failure_of_syntologys_instrument":35,"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/visual-reasoning","prev":"/task/visual-reasoning/papers/6","next":null,"papers":[{"url":null,"slug":"analysis-of-visual-reasoning-on-one-stage","title":"Analysis of Visual Reasoning on One-Stage Object Detection","date":"2022-02-26","arxiv_id":"2202.13115","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-clevrness-blackbox-testing-of","title":"Measuring CLEVRness: Blackbox testing of Visual Reasoning Models","date":"2022-02-24","arxiv_id":"2202.12162","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-of-emerging-research-directions-in","title":"A Review of Emerging Research Directions in Abstract Visual Reasoning","date":"2022-02-21","arxiv_id":"2202.10284","repositories_listed":0,"syntology":null},{"url":null,"slug":"grammar-based-grounded-lexicon-learning-1","title":"Grammar-Based Grounded Lexicon Learning","date":"2022-02-17","arxiv_id":"2202.08806","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-discrete-communication-bottlenecks","title":"Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization","date":"2022-02-02","arxiv_id":"2202.01334","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-methods-for-abstract-visual","title":"Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices","date":"2022-01-28","arxiv_id":"2201.12382","repositories_listed":0,"syntology":null},{"url":null,"slug":"deconfounded-visual-grounding","title":"Deconfounded Visual Grounding","date":"2021-12-31","arxiv_id":"2112.15324","repositories_listed":0,"syntology":null},{"url":null,"slug":"ptr-a-benchmark-for-part-based-conceptual-1","title":"PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning","date":"2021-12-09","arxiv_id":"2112.05136","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-visual-reasoning-via-language-guided","title":"Robust Visual Reasoning via Language Guided Neural Module Networks","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-in-depth-experimental-study-of-sensor","title":"An in-depth experimental study of sensor usage and visual reasoning of robots navigating in real environments","date":"2021-11-29","arxiv_id":"2111.14666","repositories_listed":0,"syntology":null},{"url":null,"slug":"recurrent-vision-transformer-for-solving","title":"Recurrent Vision Transformer for Solving Visual Reasoning Problems","date":"2021-11-29","arxiv_id":"2111.14576","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-shot-visual-reasoning-on-rpms-with-an","title":"Two-stage Rule-induction Visual Reasoning on RPMs with an Application to Video Prediction","date":"2021-11-24","arxiv_id":"2111.12301","repositories_listed":0,"syntology":null},{"url":null,"slug":"co-vqa-answering-by-interactive-sub-question","title":"Co-VQA : Answering by Interactive Sub Question Sequence","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-visual-reasoning-by-learning","title":"Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language","date":"2021-10-28","arxiv_id":"2110.15358","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-guided-bidirectional-program-search","title":"Neural-guided, Bidirectional Program Search for Abstraction and Reasoning","date":"2021-10-22","arxiv_id":"2110.11536","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-structure-mapping-for-learning-1","title":"Neural Structure Mapping For Learning Abstract Visual Analogies","date":"2021-10-12","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/inferno-inferring-object-centric-3d-scene","slug":"inferno-inferring-object-centric-3d-scene","title":"INFERNO: Inferring Object-Centric 3D Scene Representations without Supervision","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-clevrness-black-box-testing-of","title":"Measuring CLEVRness: Black-box Testing of Visual Reasoning Models","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"daren-a-collaborative-approach-towards","title":"DAReN: A Collaborative Approach Towards Reasoning And Disentangling","date":"2021-09-27","arxiv_id":"2109.13156","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-relative-spatial-reasoning","title":"Weakly Supervised Relative Spatial Reasoning for Visual Question Answering","date":"2021-09-04","arxiv_id":"2109.01934","repositories_listed":0,"syntology":null},{"url":null,"slug":"valse-a-task-independent-benchmark-for-vision","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models centered on Linguistic Phenomena","date":"2021-08-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-the-computational-demands","title":"Understanding the computational demands underlying visual reasoning","date":"2021-08-08","arxiv_id":"2108.03603","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-inter-modality-visual-parsing-with","title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training","date":"2021-06-25","arxiv_id":"2106.13488","repositories_listed":0,"syntology":null},{"url":null,"slug":"explicit-knowledge-incorporation-for-visual","title":"Explicit Knowledge Incorporation for Visual Reasoning","date":"2021-06-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/probing-inter-modality-visual-parsing-with-1","slug":"probing-inter-modality-visual-parsing-with-1","title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-and-Language Pre-training","date":"2021-05-21","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"proposal-free-one-stage-referring-expression","title":"Proposal-free One-stage Referring Expression via Grid-Word Cross-Attention","date":"2021-05-05","arxiv_id":"2105.02061","repositories_listed":0,"syntology":null},{"url":null,"slug":"chop-chop-bert-visual-question-answering-by","title":"Chop Chop BERT: Visual Question Answering by Chopping VisualBERT's Heads","date":"2021-04-30","arxiv_id":"2104.14741","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-visual-reasoning-in-humans-and-ai","title":"Comparing Visual Reasoning in Humans and AI","date":"2021-04-29","arxiv_id":"2104.14102","repositories_listed":0,"syntology":null},{"url":null,"slug":"just-because-you-are-right-doesn-t-mean-i-am-1","title":"`Just because you are right, doesn't mean I am wrong': Overcoming a bottleneck in development and evaluation of Open-Ended VQA tasks","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/agqa-a-benchmark-for-compositional-spatio","slug":"agqa-a-benchmark-for-compositional-spatio","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","date":"2021-03-30","arxiv_id":"2103.16002","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-physical-concepts-of-objects-and","title":"Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning","date":"2021-03-30","arxiv_id":"2103.16564","repositories_listed":0,"syntology":null},{"url":"/paper/acre-abstract-causal-reasoning-beyond","slug":"acre-abstract-causal-reasoning-beyond","title":"ACRE: Abstract Causal REasoning Beyond Covariation","date":"2021-03-26","arxiv_id":"2103.14232","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-data-augmentation-method-by-mixing-up","title":"Data augmentation by morphological mixup for solving Raven's Progressive Matrices","date":"2021-03-09","arxiv_id":"2103.05222","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-visual-reasoning-by-exploiting-the","title":"Improving Scene Graph Classification by Exploiting Knowledge from Texts","date":"2021-02-09","arxiv_id":"2102.04760","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-over-vision-and-language-exploring","title":"Reasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledge","date":"2021-01-15","arxiv_id":"2101.06013","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformers-in-vision-a-survey","title":"Transformers in Vision: A Survey","date":"2021-01-04","arxiv_id":"2101.01169","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-physical-object-and-event-concepts","title":"Grounding Physical Object and Event Concepts Through Dynamic Visual Reasoning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"object-centric-diagnosis-of-visual-reasoning","title":"Object-Centric Diagnosis of Visual Reasoning","date":"2020-12-21","arxiv_id":"2012.11587","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-captioning-using-weak-annotation","title":"Video Captioning Using Weak Annotation","date":"2020-09-02","arxiv_id":"2009.01067","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-visual-reasoning-via","title":"Interpretable Visual Reasoning via Probabilistic Formulation under Natural Supervision","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"trrnet-tiered-relation-reasoning-for","title":"TRRNet: Tiered Relation Reasoning for Compositional Visual Question Answering","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-visual-reasoning-with-meta","title":"Few-shot Visual Reasoning with Meta-analogical Contrastive Learning","date":"2020-07-23","arxiv_id":"2007.12020","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-granularity-modularized-network-for","title":"Multi-Granularity Modularized Network for Abstract Visual Reasoning","date":"2020-07-09","arxiv_id":"2007.04670","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-segregating-and-coordinated-segregating","title":"Self-Segregating and Coordinated-Segregating Transformer for Focused Deep Multi-Modular Network for Visual Question Answering","date":"2020-06-25","arxiv_id":"2006.14264","repositories_listed":0,"syntology":null},{"url":"/paper/neuro-symbolic-visual-reasoning-disentangling","slug":"neuro-symbolic-visual-reasoning-disentangling","title":"Neuro-Symbolic Visual Reasoning: Disentangling \"Visual\" from \"Reasoning\"","date":"2020-06-20","arxiv_id":"2006.11524","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/neuro-symbolic-visual-reasoning-disentangling#ran","syntology_url":"https://syntology.ai/paper/2006.11524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11524"}},"official":null}},{"url":null,"slug":"abstract-diagrammatic-reasoning-with-1","title":"Abstract Diagrammatic Reasoning with Multiplex Graph Networks","date":"2020-06-19","arxiv_id":"2006.11197","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-visual-reasoning-learning-to-predict","title":"Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Image","date":"2020-06-09","arxiv_id":"2006.05398","repositories_listed":0,"syntology":null},{"url":null,"slug":"webly-supervised-knowledge-embedding-model","title":"Webly Supervised Knowledge Embedding Model for Visual Reasoning","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieving-and-highlighting-action-with","title":"Retrieving and Highlighting Action with Spatiotemporal Reference","date":"2020-05-19","arxiv_id":"2005.09183","repositories_listed":0,"syntology":null},{"url":null,"slug":"shop-vrb-a-visual-reasoning-benchmark-for","title":"SHOP-VRB: A Visual Reasoning Benchmark for Object Perception","date":"2020-04-06","arxiv_id":"2004.02673","repositories_listed":0,"syntology":null},{"url":"/paper/textcaps-a-dataset-for-image-captioning-with","slug":"textcaps-a-dataset-for-image-captioning-with","title":"TextCaps: a Dataset for Image Captioning with Reading Comprehension","date":"2020-03-24","arxiv_id":"2003.12462","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-rope-manipulation-policies-using","title":"Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data","date":"2020-03-03","arxiv_id":"2003.01835","repositories_listed":0,"syntology":null},{"url":"/paper/cops-ref-a-new-dataset-and-task-on","slug":"cops-ref-a-new-dataset-and-task-on","title":"Cops-Ref: A new Dataset and Task on Compositional Referring Expression Comprehension","date":"2020-03-01","arxiv_id":"2003.00403","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-in-visual-and-relational","title":"Transfer Learning in Visual and Relational Reasoning","date":"2019-11-27","arxiv_id":"1911.11938","repositories_listed":0,"syntology":null},{"url":null,"slug":"chartnet-visual-reasoning-over-statistical","title":"ChartNet: Visual Reasoning over Statistical Charts using MAC-Networks","date":"2019-11-21","arxiv_id":"1911.09375","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-gestalt-visual-reasoning-on-the","title":"Modeling Gestalt Visual Reasoning on the Raven's Progressive Matrices Intelligence Test Using Generative Image Inpainting Techniques","date":"2019-11-18","arxiv_id":"1911.07736","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-on-abstract-visual-reasoning","title":"Attention on Abstract Visual Reasoning","date":"2019-11-14","arxiv_id":"1911.05990","repositories_listed":0,"syntology":null},{"url":null,"slug":"big-generalizations-with-small-data-exploring","title":"Big Generalizations with Small Data: Exploring the Role of Training Samples in Learning Adjectives of Size","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"modulated-self-attention-convolutional","title":"Modulated Self-attention Convolutional Network for VQA","date":"2019-10-08","arxiv_id":"1910.03343","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-abstract-visual-reasoning-with","title":"Few-Shot Abstract Visual Reasoning With Spectral Features","date":"2019-10-04","arxiv_id":"1910.01833","repositories_listed":0,"syntology":null},{"url":null,"slug":"highlighting-bias-with-explainable-neural","title":"Towards Explainable Neural-Symbolic Visual Reasoning","date":"2019-09-19","arxiv_id":"1909.09065","repositories_listed":0,"syntology":null},{"url":null,"slug":"procedural-reasoning-networks-for","title":"Procedural Reasoning Networks for Understanding Multimodal Procedures","date":"2019-09-19","arxiv_id":"1909.08859","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-graph-attention-for-referring","title":"Dynamic Graph Attention for Referring Expression Comprehension","date":"2019-09-18","arxiv_id":"1909.08164","repositories_listed":0,"syntology":null},{"url":null,"slug":"modelling-working-memory-using-deep-recurrent","title":"Modelling Working Memory using Deep Recurrent Reinforcement Learning","date":"2019-09-11","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"v-prom-a-benchmark-for-visual-reasoning-using","title":"V-PROM: A Benchmark for Visual Reasoning Using Visual Progressive Matrices","date":"2019-07-29","arxiv_id":"1907.12271","repositories_listed":0,"syntology":null},{"url":null,"slug":"2nd-place-solution-to-the-gqa-challenge-2019","title":"2nd Place Solution to the GQA Challenge 2019","date":"2019-07-16","arxiv_id":"1907.06794","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-compose-and-reason-with-language","title":"Learning to Compose and Reason with Language Tree Structures for Visual Grounding","date":"2019-06-05","arxiv_id":"1906.01784","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-search-for-weakly-supervised","title":"Iterative Search for Weakly Supervised Semantic Parsing","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"its-not-about-the-journey-its-about-the","title":"It's Not About the Journey; It's About the Destination: Following Soft Paths Under Question-Guidance for Visual Reasoning","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/social-iq-a-question-answering-benchmark-for","slug":"social-iq-a-question-answering-benchmark-for","title":"Social-IQ: A Question Answering Benchmark for Artificial Social Intelligence","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"are-disentangled-representations-helpful-for","title":"Are Disentangled Representations Helpful for Abstract Visual Reasoning?","date":"2019-05-29","arxiv_id":"1905.12506","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reason-a-strong-baseline-for-real-world","title":"Deep Reason: A Strong Baseline for Real-World Visual Reasoning","date":"2019-05-24","arxiv_id":"1905.10226","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-collocate-neural-modules-for","title":"Learning to Collocate Neural Modules for Image Captioning","date":"2019-04-18","arxiv_id":"1904.08608","repositories_listed":0,"syntology":null},{"url":null,"slug":"question-guided-modular-routing-networks-for","title":"Question Guided Modular Routing Networks for Visual Question Answering","date":"2019-04-17","arxiv_id":"1904.08324","repositories_listed":0,"syntology":null},{"url":"/paper/raven-a-dataset-for-relational-and-analogical","slug":"raven-a-dataset-for-relational-and-analogical","title":"RAVEN: A Dataset for Relational and Analogical Visual rEasoNing","date":"2019-03-07","arxiv_id":"1903.02741","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-visual-to-acoustic-question-answering","title":"From Visual to Acoustic Question Answering","date":"2019-02-28","arxiv_id":"1902.11280","repositories_listed":0,"syntology":null},{"url":"/paper/making-history-matter-gold-critic-sequence","slug":"making-history-matter-gold-critic-sequence","title":"Making History Matter: History-Advantage Sequence Training for Visual Dialog","date":"2019-02-25","arxiv_id":"1902.09326","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-we-automate-diagrammatic-reasoning","title":"Can We Automate Diagrammatic Reasoning?","date":"2019-02-13","arxiv_id":"1902.04955","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-reasoning-of-feature-attribution-with","title":"Visual Reasoning of Feature Attribution with Deep Recurrent Neural Networks","date":"2019-01-17","arxiv_id":"1901.05574","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-knowledge-distillation-to-aid-visual","title":"Spatial Knowledge Distillation to aid Visual Reasoning","date":"2018-12-10","arxiv_id":"1812.03631","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainability-by-parsing-neural-module-tree","title":"Learning to Assemble Neural Module Tree Networks for Visual Grounding","date":"2018-12-08","arxiv_id":"1812.03299","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-semantic-parsing-with","title":"Weakly Supervised Semantic Parsing with Abstract Examples","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"modularity-matters-learning-invariant","title":"Modularity Matters: Learning Invariant Relational Reasoning Tasks","date":"2018-06-18","arxiv_id":"1806.06765","repositories_listed":0,"syntology":null},{"url":null,"slug":"lexical-conceptual-structure-of-literal-and","title":"Lexical Conceptual Structure of Literal and Metaphorical Spatial Language: A Case Study of ``Push''","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"object-ordering-with-bidirectional-matchings","title":"Object Ordering with Bidirectional Matchings for Visual Reasoning","date":"2018-04-18","arxiv_id":"1804.06870","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-visual-reasoning-beyond","title":"Iterative Visual Reasoning Beyond Convolutions","date":"2018-03-29","arxiv_id":"1803.11189","repositories_listed":0,"syntology":null},{"url":null,"slug":"same-different-problems-strain-convolutional","title":"Same-different problems strain convolutional neural networks","date":"2018-02-09","arxiv_id":"1802.03390","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmark-visual-question-answer-models-by","title":"Benchmark Visual Question Answer Models by using Focus Map","date":"2018-01-13","arxiv_id":"1801.05302","repositories_listed":0,"syntology":null},{"url":null,"slug":"not-so-clevr-visual-relations-strain","title":"Not-So-CLEVR: Visual Relations Strain Feedforward Neural Networks","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/learning-to-act-properly-predicting-and","slug":"learning-to-act-properly-predicting-and","title":"Learning to Act Properly: Predicting and Explaining Affordances from Images","date":"2017-12-20","arxiv_id":"1712.07576","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-reasoning-with-natural-language","title":"Visual Reasoning with Natural Language","date":"2017-10-02","arxiv_id":"1710.00453","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-learning-of-semantic-grasping","title":"End-to-End Learning of Semantic Grasping","date":"2017-07-06","arxiv_id":"1707.01932","repositories_listed":0,"syntology":null},{"url":"/paper/a-corpus-of-natural-language-for-visual","slug":"a-corpus-of-natural-language-for-visual","title":"A Corpus of Natural Language for Visual Reasoning","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"egoreid-cross-view-self-identification-and","title":"EgoReID: Cross-view Self-Identification and Human Re-identification in Egocentric and Surveillance Videos","date":"2016-12-24","arxiv_id":"1612.08153","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-local-global-contextual-pathways-for","title":"Dual Local-Global Contextual Pathways for Recognition in Aerial Imagery","date":"2016-05-18","arxiv_id":"1605.05462","repositories_listed":0,"syntology":null},{"url":null,"slug":"filling-in-the-details-perceiving-from-low","title":"Filling in the details: Perceiving from low fidelity images","date":"2016-04-14","arxiv_id":"1604.04125","repositories_listed":0,"syntology":null},{"url":"/paper/are-elephants-bigger-than-butterflies","slug":"are-elephants-bigger-than-butterflies","title":"Are Elephants Bigger than Butterflies? Reasoning about Sizes of Objects","date":"2016-02-02","arxiv_id":"1602.00753","repositories_listed":0,"syntology":null},{"url":null,"slug":"factorization-of-view-object-manifolds-for","title":"Factorization of View-Object Manifolds for Joint Object Recognition and Pose Estimation","date":"2015-03-23","arxiv_id":"1503.06813","repositories_listed":0,"syntology":null}],"record_sha256":"7413aca31244a87ff09eaf1aa2a79843ae26f7d5adde855660ed15e9f50bbcc9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}