{"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":"/paper/compact-bilinear-pooling","title":"Compact Bilinear Pooling","arxiv_id":"1511.06062","date":"2015-11-19","proceeding":"CVPR 2016 6","authors":["Yang Gao","Oscar Beijbom","Ning Zhang","Trevor Darrell"],"abstract":"Bilinear models has been shown to achieve impressive performance on a wide\nrange of visual tasks, such as semantic segmentation, fine grained recognition\nand face recognition. However, bilinear features are high dimensional,\ntypically on the order of hundreds of thousands to a few million, which makes\nthem impractical for subsequent analysis. We propose two compact bilinear\nrepresentations with the same discriminative power as the full bilinear\nrepresentation but with only a few thousand dimensions. Our compact\nrepresentations allow back-propagation of classification errors enabling an\nend-to-end optimization of the visual recognition system. The compact bilinear\nrepresentations are derived through a novel kernelized analysis of bilinear\npooling which provide insights into the discriminative power of bilinear\npooling, and a platform for further research in compact pooling methods.\nExperimentation illustrate the utility of the proposed representations for\nimage classification and few-shot learning across several datasets.","url_abs":"http://arxiv.org/abs/1511.06062v2","url_pdf":"http://arxiv.org/pdf/1511.06062v2.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":"compact-bilinear-pooling","repo_url":"https://github.com/gy20073/compact_bilinear_pooling","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"compact-bilinear-pooling","repo_url":"https://github.com/Seth-Park/MultimodalExplanations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":null},{"paper_slug":"compact-bilinear-pooling","repo_url":"https://github.com/akirafukui/vqa-mcb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"compact-bilinear-pooling","repo_url":"https://github.com/aniket03/keras_compact_bilnear_CNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"compact-bilinear-pooling","repo_url":"https://github.com/divelab/vqa-text","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":{"status":"ok"}},{"paper_slug":"compact-bilinear-pooling","repo_url":"https://github.com/jnhwkim/cbp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"compact-bilinear-pooling","repo_url":"https://github.com/Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1511.06062","atlas_url":"https://app.syntology.ai/?focus=1511.06062","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1511.06062"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1511.06062\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1511.06062"},"call":"get_concepts_for_paper(arxiv_id=\"1511.06062\")"}],"by_repo":[{"repo":"gy20073/compact_bilinear_pooling","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Seth-Park/MultimodalExplanations","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1802.08129"],"harvested_for_calls":[{"arxiv_id":"1802.08129","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1802.08129"},"call":"get_harvested_code_for_paper(arxiv_id=\"1802.08129\")"}]},{"repo":"akirafukui/vqa-mcb","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1606.07356"],"harvested_for_calls":[{"arxiv_id":"1606.07356","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1606.07356"},"call":"get_harvested_code_for_paper(arxiv_id=\"1606.07356\")"}]},{"repo":"aniket03/keras_compact_bilnear_CNN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"divelab/vqa-text","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jnhwkim/cbp","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"5040b71b6d0da28abeaa9ec9741798d2d41f4be6f53c4a590ca5da6237e85144","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}