{"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/cross-modal-retrieval/papers/5","list_of":"/task/cross-modal-retrieval","task":"Cross-Modal Retrieval","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":5,"pages_in_order":6,"rows_per_page":100,"rows":[401,500],"of":522,"counts":{"archive_papers_tagged":522,"with_a_code_link":244,"where_syntology_ran_a_sample":70,"not_listed_spam_title":0,"listed":522,"listed_where_code_ran":70,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":56,"every_run_a_failure_of_syntologys_instrument":14,"listed_with_a_run_with_no_instrument_failure":56,"listed_every_run_a_failure_of_syntologys_instrument":14,"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/cross-modal-retrieval","prev":"/task/cross-modal-retrieval/papers/4","next":"/task/cross-modal-retrieval/papers/6","papers":[{"url":null,"slug":"variational-autoencoder-with-cca-for-audio","title":"Variational Autoencoder with CCA for Audio-Visual Cross-Modal Retrieval","date":"2021-12-05","arxiv_id":"2112.02601","repositories_listed":0,"syntology":null},{"url":null,"slug":"swamp-swapped-assignment-of-multi-modal-pairs","title":"SwAMP: Swapped Assignment of Multi-Modal Pairs for Cross-Modal Retrieval","date":"2021-11-10","arxiv_id":"2111.05814","repositories_listed":0,"syntology":null},{"url":null,"slug":"inflate-and-shrink-enriching-and-reducing","title":"Inflate and Shrink:Enriching and Reducing Interactions for Fast Text-Image Retrieval","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mural-multimodal-multitask-representations","title":"MURAL: Multimodal, Multitask Representations Across Languages","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"vldeformer-learning-visual-semantic","title":"VLDeformer: Vision-Language Decomposed Transformer for Fast Cross-Modal Retrieval","date":"2021-10-20","arxiv_id":"2110.11338","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-structural-representations-for","title":"Learning Structural Representations for Recipe Generation and Food Retrieval","date":"2021-10-04","arxiv_id":"2110.01209","repositories_listed":0,"syntology":null},{"url":null,"slug":"calibrating-probabilistic-embeddings-for","title":"Calibrating Probabilistic Embeddings for Cross-Modal Retrieval","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-modality-invariant-and","title":"Self-Supervised Modality-Invariant and Modality-Specific Feature Learning for 3D Objects","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficientclip-efficient-cross-modal-pre","title":"EfficientCLIP: Efficient Cross-Modal Pre-training by Ensemble Confident Learning and Language Modeling","date":"2021-09-10","arxiv_id":"2109.04699","repositories_listed":0,"syntology":null},{"url":"/paper/mural-multimodal-multitask-retrieval-across","slug":"mural-multimodal-multitask-retrieval-across","title":"MURAL: Multimodal, Multitask Retrieval Across Languages","date":"2021-09-10","arxiv_id":"2109.05125","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-joint-embedding-with-modality","title":"Learning Joint Embedding with Modality Alignments for Cross-Modal Retrieval of Recipes and Food Images","date":"2021-08-09","arxiv_id":"2108.03788","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-pattern-loss-based-diversified","title":"Graph Pattern Loss based Diversified Attention Network for Cross-Modal Retrieval","date":"2021-06-25","arxiv_id":"2106.13552","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-center-loss-for-3d-cross-modal","title":"Cross-Modal Center Loss for 3D Cross-Modal Retrieval","date":"2021-06-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-relational-graph-for-cross-modal","title":"Multi-Modal Relational Graph for Cross-Modal Video Moment Retrieval","date":"2021-06-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-discrete-representation-learning","title":"Cross-Modal Discrete Representation Learning","date":"2021-06-10","arxiv_id":"2106.05438","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-cross-modal-pretraining-for","title":"Cross-lingual Cross-modal Pretraining for Multimodal Retrieval","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-efficient-cross-modal-visual-textual","title":"Towards Efficient Cross-Modal Visual Textual Retrieval using Transformer-Encoder Deep Features","date":"2021-06-01","arxiv_id":"2106.00358","repositories_listed":0,"syntology":null},{"url":null,"slug":"more-than-just-attention-learning-cross-modal","title":"More Than Just Attention: Improving Cross-Modal Attentions with Contrastive Constraints for Image-Text Matching","date":"2021-05-20","arxiv_id":"2105.09597","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-dense-video-captioning-via","title":"Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching","date":"2021-05-18","arxiv_id":"2105.08252","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-and-multimodal-data-analysis","title":"Cross-Modal and Multimodal Data Analysis Based on Functional Mapping of Spectral Descriptors and Manifold Regularization","date":"2021-05-12","arxiv_id":"2105.05631","repositories_listed":0,"syntology":null},{"url":null,"slug":"t-emde-sketching-based-global-similarity-for","title":"T-EMDE: Sketching-based global similarity for cross-modal retrieval","date":"2021-05-10","arxiv_id":"2105.04242","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-contrastive-training-for-visual","title":"Multimodal Contrastive Training for Visual Representation Learning","date":"2021-04-26","arxiv_id":"2104.12836","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-retrieval-augmentation-for-multi-1","title":"Cross-Modal Retrieval Augmentation for Multi-Modal Classification","date":"2021-04-16","arxiv_id":"2104.08108","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-learning-in-cross-modal-retrieval","title":"Continual learning in cross-modal retrieval","date":"2021-04-14","arxiv_id":"2104.06806","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-information-theory-and","title":"Integrating Information Theory and Adversarial Learning for Cross-modal Retrieval","date":"2021-04-11","arxiv_id":"2104.04991","repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminative-semantic-transitive","title":"Discriminative Semantic Transitive Consistency for Cross-Modal Learning","date":"2021-03-25","arxiv_id":"2103.14103","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-image-retrieval-with-deep-mutual","title":"Cross-modal Image Retrieval with Deep Mutual Information Maximization","date":"2021-03-10","arxiv_id":"2103.06032","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-attack-on-deep-cross-modal","title":"Adversarial Attack on Deep Cross-Modal Hamming Retrieval","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"wasserstein-coupled-graph-learning-for-cross","title":"Wasserstein Coupled Graph Learning for Cross-Modal Retrieval","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/cross-modal-retrieval-and-synthesis-x-mrs","slug":"cross-modal-retrieval-and-synthesis-x-mrs","title":"Cross-Modal Retrieval and Synthesis (X-MRS): Closing the Modality Gap in Shared Representation Learning","date":"2020-12-02","arxiv_id":"2012.01345","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-disentangled-latent-factors-from","title":"Learning Disentangled Latent Factors from Paired Data in Cross-Modal Retrieval: An Implicit Identifiable VAE Approach","date":"2020-12-01","arxiv_id":"2012.00682","repositories_listed":0,"syntology":null},{"url":null,"slug":"mtm-dataset-for-joint-representation-learning","title":"MusicTM-Dataset for Joint Representation Learning among Sheet Music, Lyrics, and Musical Audio","date":"2020-12-01","arxiv_id":"2012.00290","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-cross-modal-proxy-hashing","title":"Deep Cross-modal Hashing via Margin-dynamic-softmax Loss","date":"2020-11-06","arxiv_id":"2011.03451","repositories_listed":0,"syntology":null},{"url":null,"slug":"ink-marker-segmentation-in-histopathology","title":"Ink Marker Segmentation in Histopathology Images Using Deep Learning","date":"2020-10-29","arxiv_id":"2010.15865","repositories_listed":0,"syntology":null},{"url":null,"slug":"new-ideas-and-trends-in-deep-multimodal","title":"New Ideas and Trends in Deep Multimodal Content Understanding: A Review","date":"2020-10-16","arxiv_id":"2010.08189","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-visual-semantic-embeddings-for","title":"Learning Visual-Semantic Embeddings for Reporting Abnormal Findings on Chest X-rays","date":"2020-10-06","arxiv_id":"2010.02467","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-center-loss","title":"Cross-modal Center Loss","date":"2020-08-08","arxiv_id":"2008.03561","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-deep-cross-modality-spectral","title":"Unsupervised Deep Cross-modality Spectral Hashing","date":"2020-08-01","arxiv_id":"2008.00223","repositories_listed":0,"syntology":null},{"url":null,"slug":"preserving-semantic-neighborhoods-for-robust","title":"Preserving Semantic Neighborhoods for Robust Cross-modal Retrieval","date":"2020-07-16","arxiv_id":"2007.08617","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-view-orthonormalized-partial-least","title":"Multi-view Orthonormalized Partial Least Squares: Regularizations and Deep Extensions","date":"2020-07-09","arxiv_id":"2007.05028","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-modal-and-view-invariant","title":"Self-supervised Modal and View Invariant Feature Learning","date":"2020-05-28","arxiv_id":"2005.14169","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":"cross-view-image-retrieval-ground-to-aerial","title":"Cross-View Image Retrieval -- Ground to Aerial Image Retrieval through Deep Learning","date":"2020-05-02","arxiv_id":"2005.00725","repositories_listed":0,"syntology":null},{"url":null,"slug":"mediapi-skel-a-2d-skeleton-video-database-of","title":"MEDIAPI-SKEL - A 2D-Skeleton Video Database of French Sign Language With Aligned French Subtitles","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mcen-bridging-cross-modal-gap-between-cooking","title":"MCEN: Bridging Cross-Modal Gap between Cooking Recipes and Dish Images with Latent Variable Model","date":"2020-04-02","arxiv_id":"2004.01095","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-adaptive-asymmetric-deep-cross-modal","title":"Task-adaptive Asymmetric Deep Cross-modal Hashing","date":"2020-04-01","arxiv_id":"2004.00197","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-domain-independent-feature","title":"Progressive Domain-Independent Feature Decomposition Network for Zero-Shot Sketch-Based Image Retrieval","date":"2020-03-22","arxiv_id":"2003.09869","repositories_listed":0,"syntology":null},{"url":"/paper/cross-modal-food-retrieval-learning-a-joint","slug":"cross-modal-food-retrieval-learning-a-joint","title":"Cross-Modal Food Retrieval: Learning a Joint Embedding of Food Images and Recipes with Semantic Consistency and Attention Mechanism","date":"2020-03-09","arxiv_id":"2003.03955","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-multimodal-image-text-embeddings-for","title":"Deep Multimodal Image-Text Embeddings for Automatic Cross-Media Retrieval","date":"2020-02-23","arxiv_id":"2002.10016","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-instance-level-sketch-based","title":"Fine-Grained Instance-Level Sketch-Based Video Retrieval","date":"2020-02-21","arxiv_id":"2002.09461","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-robust-multilevel-semantic-cross-modal","title":"Deep Robust Multilevel Semantic Cross-Modal Hashing","date":"2020-02-07","arxiv_id":"2002.02698","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-incremental-cross-modal-hashing","title":"A Novel Incremental Cross-Modal Hashing Approach","date":"2020-02-03","arxiv_id":"2002.00677","repositories_listed":0,"syntology":null},{"url":null,"slug":"asymmetric-correlation-quantization-hashing","title":"Asymmetric Correlation Quantization Hashing for Cross-modal Retrieval","date":"2020-01-14","arxiv_id":"2001.04625","repositories_listed":0,"syntology":null},{"url":null,"slug":"dividing-and-conquering-cross-modal-recipe","title":"Dividing and Conquering Cross-Modal Recipe Retrieval: from Nearest Neighbours Baselines to SoTA","date":"2019-11-28","arxiv_id":"1911.12763","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-proposal-based-approach-for-activity-image","title":"A Proposal-based Approach for Activity Image-to-Video Retrieval","date":"2019-11-24","arxiv_id":"1911.10531","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-latent-space-learning-for-cross-modal","title":"Deep Latent Space Learning for Cross-modal Mapping of Audio and Visual Signals","date":"2019-09-18","arxiv_id":"1909.08685","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-wasserstein-autoencoders-for-aligning","title":"Joint Wasserstein Autoencoders for Aligning Multimodal Embeddings","date":"2019-09-14","arxiv_id":"1909.06635","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-cross-modal-systems-leverage-semantic","title":"Do Cross Modal Systems Leverage Semantic Relationships?","date":"2019-09-03","arxiv_id":"1909.01976","repositories_listed":0,"syntology":null},{"url":null,"slug":"artpedia","title":"Artpedia","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"190807673","title":"Learning Joint Embedding for Cross-Modal Retrieval","date":"2019-08-21","arxiv_id":"1908.07673","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-action-retrieval-through","title":"Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings","date":"2019-08-09","arxiv_id":"1908.03477","repositories_listed":0,"syntology":null},{"url":null,"slug":"multisensory-learning-framework-for-robot","title":"Multisensory Learning Framework for Robot Drumming","date":"2019-07-23","arxiv_id":"1907.09775","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-soft-attention-models-for-tempo","title":"Learning Soft-Attention Models for Tempo-invariant Audio-Sheet Music Retrieval","date":"2019-06-26","arxiv_id":"1906.10996","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modality-personalization-for-retrieval","title":"Cross-Modality Personalization for Retrieval","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"label-prediction-framework-for-semi","title":"Label Prediction Framework for Semi-Supervised Cross-Modal Retrieval","date":"2019-05-27","arxiv_id":"1905.11139","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-text-image-matching-by-mitigating","title":"Improved Text-Image Matching by Mitigating Visual Semantic Hubs","date":"2019-05-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-unified-multimodal-embeddings-for","title":"Deep Unified Multimodal Embeddings for Understanding both Content and Users in Social Media Networks","date":"2019-05-17","arxiv_id":"1905.07075","repositories_listed":0,"syntology":null},{"url":null,"slug":"ranking-based-deep-cross-modal-hashing","title":"Ranking-based Deep Cross-modal Hashing","date":"2019-05-11","arxiv_id":"1905.04450","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-adversarial-network-for-zero-shot","title":"Semantic Adversarial Network for Zero-Shot Sketch-Based Image Retrieval","date":"2019-05-07","arxiv_id":"1905.02327","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-discrete-supervised-hashing-for","title":"Efficient Discrete Supervised Hashing for Large-scale Cross-modal Retrieval","date":"2019-05-03","arxiv_id":"1905.01304","repositories_listed":0,"syntology":null},{"url":null,"slug":"fusion-supervised-deep-cross-modal-hashing","title":"Fusion-supervised Deep Cross-modal Hashing","date":"2019-04-25","arxiv_id":"1904.11171","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-cross-modal-retrieval-via","title":"Adversarial Cross-Modal Retrieval via Learning and Transferring Single-Modal Similarities","date":"2019-04-17","arxiv_id":"1904.08042","repositories_listed":0,"syntology":null},{"url":null,"slug":"triplet-based-deep-hashing-network-for-cross","title":"Triplet-Based Deep Hashing Network for Cross-Modal Retrieval","date":"2019-04-04","arxiv_id":"1904.02449","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-concatenation-hashing-with","title":"Unsupervised Multi-modal Hashing for Cross-modal retrieval","date":"2019-03-26","arxiv_id":"1904.00726","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-embodied-semantics-via-music-and","title":"Learning Embodied Semantics via Music and Dance Semiotic Correlations","date":"2019-03-25","arxiv_id":"1903.10534","repositories_listed":0,"syntology":null},{"url":null,"slug":"coupled-cyclegan-unsupervised-hashing-network","title":"Coupled CycleGAN: Unsupervised Hashing Network for Cross-Modal Retrieval","date":"2019-03-06","arxiv_id":"1903.02149","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-music-retrieval-and-applications","title":"Cross-Modal Music Retrieval and Applications: An Overview of Key Methodologies","date":"2019-02-12","arxiv_id":"1902.04397","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-visual-representations-for","title":"Self-Supervised Visual Representations for Cross-Modal Retrieval","date":"2019-01-31","arxiv_id":"1902.00378","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-semantic-multimodal-hashing-network-for","title":"Deep Semantic Multimodal Hashing Network for Scalable Image-Text and Video-Text Retrievals","date":"2019-01-09","arxiv_id":"1901.02662","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-semantic-correlation-learning-based","title":"Deep Semantic Correlation Learning Based Hashing for Multimedia Cross-Modal Retrieval","date":"2018-12-31","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminative-supervised-hashing-for-cross","title":"Discriminative Supervised Hashing for Cross-Modal similarity Search","date":"2018-12-06","arxiv_id":"1812.07660","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-learning-framework-for-semi-supervised","title":"Semi-Supervised Cross-Modal Retrieval with Label Prediction","date":"2018-12-04","arxiv_id":"1812.01391","repositories_listed":0,"syntology":null},{"url":null,"slug":"y2seq2seq-cross-modal-representation-learning","title":"Y^2Seq2Seq: Cross-Modal Representation Learning for 3D Shape and Text by Joint Reconstruction and Prediction of View and Word Sequences","date":"2018-11-07","arxiv_id":"1811.02745","repositories_listed":0,"syntology":null},{"url":"/paper/recipe1m-a-dataset-for-learning-cross-modal","slug":"recipe1m-a-dataset-for-learning-cross-modal","title":"Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images","date":"2018-10-14","arxiv_id":"1810.06553","repositories_listed":0,"syntology":null},{"url":null,"slug":"dense-multimodal-fusion-for-hierarchically","title":"Dense Multimodal Fusion for Hierarchically Joint Representation","date":"2018-10-08","arxiv_id":"1810.03414","repositories_listed":0,"syntology":null},{"url":null,"slug":"webly-supervised-joint-embedding-for-cross-1","title":"Webly Supervised Joint Embedding for Cross-Modal lmage-Text Retrieval","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"perfect-match-improved-cross-modal-embeddings","title":"Perfect match: Improved cross-modal embeddings for audio-visual synchronisation","date":"2018-09-21","arxiv_id":"1809.08001","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-aware-deep-adversarial-hashing-for","title":"Attention-aware Deep Adversarial Hashing for Cross-Modal Retrieval","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-hamming-hashing","title":"Cross-Modal Hamming Hashing","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"webly-supervised-joint-embedding-for-cross","title":"Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval","date":"2018-08-23","arxiv_id":"1808.07793","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-discriminative-hashing-codes-for","title":"Learning Discriminative Hashing Codes for Cross-Modal Retrieval based on Multi-view Features","date":"2018-08-13","arxiv_id":"1808.04152","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-cross-modal-retrieval","title":"Revisiting Cross Modal Retrieval","date":"2018-07-19","arxiv_id":"1807.07364","repositories_listed":0,"syntology":null},{"url":null,"slug":"category-based-deep-cca-for-fine-grained","title":"Category-Based Deep CCA for Fine-Grained Venue Discovery from Multimodal Data","date":"2018-05-08","arxiv_id":"1805.02997","repositories_listed":0,"syntology":null},{"url":null,"slug":"cycle-consistent-deep-generative-hashing-for","title":"Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval","date":"2018-04-30","arxiv_id":"1804.11013","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-retrieval-with-implicit-concept","title":"Cross-Modal Retrieval with Implicit Concept Association","date":"2018-04-12","arxiv_id":"1804.04318","repositories_listed":0,"syntology":null},{"url":null,"slug":"attribute-guided-network-for-cross-modal-zero","title":"Attribute-Guided Network for Cross-Modal Zero-Shot Hashing","date":"2018-02-06","arxiv_id":"1802.01943","repositories_listed":0,"syntology":null},{"url":null,"slug":"objects-that-sound","title":"Objects that Sound","date":"2017-12-18","arxiv_id":"1712.06651","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-deep-modeling-of-music-semantics","title":"Towards Deep Modeling of Music Semantics using EEG Regularizers","date":"2017-12-14","arxiv_id":"1712.05197","repositories_listed":0,"syntology":null},{"url":"/paper/learning-semantic-concepts-and-order-for","slug":"learning-semantic-concepts-and-order-for","title":"Learning Semantic Concepts and Order for Image and Sentence Matching","date":"2017-12-06","arxiv_id":"1712.02036","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-generative-adversarial-cross","title":"Unsupervised Generative Adversarial Cross-modal Hashing","date":"2017-12-01","arxiv_id":"1712.00358","repositories_listed":0,"syntology":null}],"record_sha256":"7c07ed322c8e819705a556bf23d49d4db7af0a9b094adaa95047e59e51671347","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}