{"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/noise-estimation-using-density-estimation-for","title":"Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning","arxiv_id":"2003.03186","date":"2020-03-06","proceeding":null,"authors":["Elad Amrani","Rami Ben-Ari","Daniel Rotman","Alex Bronstein"],"abstract":"One of the key factors of enabling machine learning models to comprehend and solve real-world tasks is to leverage multimodal data. Unfortunately, annotation of multimodal data is challenging and expensive. Recently, self-supervised multimodal methods that combine vision and language were proposed to learn multimodal representations without annotation. However, these methods often choose to ignore the presence of high levels of noise and thus yield sub-optimal results. In this work, we show that the problem of noise estimation for multimodal data can be reduced to a multimodal density estimation task. Using multimodal density estimation, we propose a noise estimation building block for multimodal representation learning that is based strictly on the inherent correlation between different modalities. We demonstrate how our noise estimation can be broadly integrated and achieves comparable results to state-of-the-art performance on five different benchmark datasets for two challenging multimodal tasks: Video Question Answering and Text-To-Video Retrieval. Furthermore, we provide a theoretical probabilistic error bound substantiating our empirical results and analyze failure cases. Code: https://github.com/elad-amrani/ssml.","url_abs":"https://arxiv.org/abs/2003.03186v3","url_pdf":"https://arxiv.org/pdf/2003.03186v3.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":"noise-estimation-using-density-estimation-for","repo_url":"https://github.com/elad-amrani/ssml","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"density-estimation","task_name":"Density Estimation"},{"task_slug":"noise-estimation","task_name":"Noise Estimation"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-to-video-retrieval","task_name":"Text to Video Retrieval"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"zero-shot-video-retrieval","task_name":"Zero-Shot Video Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-retrieval-on-msvd","task":"Video Retrieval","dataset":"MSVD","model":"SSML","rank_in_archive_order":23,"of":24,"metrics":{"text-to-video Mean Rank":"--","text-to-video Median Rank":"6.0","text-to-video R@1":"20.3","text-to-video R@10":"63.3","text-to-video R@5":"49.0","text-to-video R@50":"--"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-msrvtt-qa-2","task":"Visual Question Answering","dataset":"MSRVTT-QA","model":"SSML","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"0.35"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-msvd-qa-1","task":"Visual Question Answering (VQA)","dataset":"MSVD-QA","model":"SSML","rank_in_archive_order":33,"of":36,"metrics":{"Accuracy":"0.351"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-retrieval-on-lsmdc","task":"Zero-Shot Video Retrieval","dataset":"LSMDC","model":"SSML","rank_in_archive_order":16,"of":16,"metrics":{"text-to-video R@1":"4.2","text-to-video R@10":"17.1","text-to-video R@5":"11.6"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-retrieval-on-msr-vtt","task":"Zero-Shot Video Retrieval","dataset":"MSR-VTT","model":"SSML","rank_in_archive_order":39,"of":41,"metrics":{"text-to-video R@1":"8.0","text-to-video R@10":"29.3","text-to-video R@5":"21.3"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-retrieval-on-msvd","task":"Zero-Shot Video Retrieval","dataset":"MSVD","model":"SSML","rank_in_archive_order":14,"of":14,"metrics":{"text-to-video R@1":"13.66","text-to-video R@10":"47.74","text-to-video R@5":"35.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2003.03186","atlas_url":"https://app.syntology.ai/?focus=2003.03186","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":"2003.03186"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2003.03186\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2003.03186"},"call":"get_concepts_for_paper(arxiv_id=\"2003.03186\")"}],"by_repo":[{"repo":"elad-amrani/ssml","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"10995a4e132d5572f63abea1bf8525df2adb8763c21a1800116130068a2a1802","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}