{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/modality-agnostic-attention-fusion-for-visual","title":"Modality-Agnostic Attention Fusion for visual search with text feedback","arxiv_id":"2007.00145","date":"2020-06-30","proceeding":null,"authors":["Eric Dodds","Jack Culpepper","Simao Herdade","Yang Zhang","Kofi Boakye"],"abstract":"Image retrieval with natural language feedback offers the promise of catalog search based on fine-grained visual features that go beyond objects and binary attributes, facilitating real-world applications such as e-commerce. Our Modality-Agnostic Attention Fusion (MAAF) model combines image and text features and outperforms existing approaches on two visual search with modifying phrase datasets, Fashion IQ and CSS, and performs competitively on a dataset with only single-word modifications, Fashion200k. We also introduce two new challenging benchmarks adapted from Birds-to-Words and Spot-the-Diff, which provide new settings with rich language inputs, and we show that our approach without modification outperforms strong baselines. To better understand our model, we conduct detailed ablations on Fashion IQ and provide visualizations of the surprising phenomenon of words avoiding \"attending\" to the image region they refer to.","url_abs":"https://arxiv.org/abs/2007.00145v1","url_pdf":"https://arxiv.org/pdf/2007.00145v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"modality-agnostic-attention-fusion-for-visual","repo_url":"https://github.com/nashory/rtic-gcn-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"modality-agnostic-attention-fusion-for-visual","repo_url":"https://github.com/yahoo/maaf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2007.00145","atlas_url":"https://app.syntology.ai/?focus=2007.00145","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.00145"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nashory/rtic-gcn-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yahoo/maaf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"listed":{"samples":7,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"36bf726265cbf8fe","entry":"autotune_threshold","repo":"nashory/rtic-gcn-pytorch","repo_kind":"listed","path":"utils/gcn_utils.py","file_url":"https://github.com/nashory/rtic-gcn-pytorch/blob/HEAD/utils/gcn_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"36bf726265cbf8fe"}},{"code_sha256_prefix":"70e3fde283039da4","entry":"build_graph","repo":"nashory/rtic-gcn-pytorch","repo_kind":"listed","path":"utils/gcn_utils.py","file_url":"https://github.com/nashory/rtic-gcn-pytorch/blob/HEAD/utils/gcn_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"70e3fde283039da4"}},{"code_sha256_prefix":"d9def42110729a85","entry":"conv1x1","repo":"nashory/rtic-gcn-pytorch","repo_kind":"listed","path":"model/resnet.py","file_url":"https://github.com/nashory/rtic-gcn-pytorch/blob/HEAD/model/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"nashory/rtic-gcn-pytorch","repo_kind":"listed","path":"model/resnet.py","file_url":"https://github.com/nashory/rtic-gcn-pytorch/blob/HEAD/model/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"160bb14bd76201b4"}},{"code_sha256_prefix":"6aeac26973c32ea7","entry":"tokenize_text","repo":"nashory/rtic-gcn-pytorch","repo_kind":"listed","path":"model/base.py","file_url":"https://github.com/nashory/rtic-gcn-pytorch/blob/HEAD/model/base.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6aeac26973c32ea7"}},{"code_sha256_prefix":"ca03f91d739912f2","entry":"pairwise_distances","repo":"nashory/rtic-gcn-pytorch","repo_kind":"listed","path":"misc/loss.py","file_url":"https://github.com/nashory/rtic-gcn-pytorch/blob/HEAD/misc/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca03f91d739912f2"}},{"code_sha256_prefix":"0b2135cab7c66bb5","entry":"resnet18","repo":"nashory/rtic-gcn-pytorch","repo_kind":"listed","path":"model/resnet.py","file_url":"https://github.com/nashory/rtic-gcn-pytorch/blob/HEAD/model/resnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0b2135cab7c66bb5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}