{"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/gmmformer-gaussian-mixture-model-based","title":"GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval","arxiv_id":"2310.05195","date":"2023-10-08","proceeding":null,"authors":["Yuting Wang","Jinpeng Wang","Bin Chen","Ziyun Zeng","Shu-Tao Xia"],"abstract":"Given a text query, partially relevant video retrieval (PRVR) seeks to find untrimmed videos containing pertinent moments in a database. For PRVR, clip modeling is essential to capture the partial relationship between texts and videos. Current PRVR methods adopt scanning-based clip construction to achieve explicit clip modeling, which is information-redundant and requires a large storage overhead. To solve the efficiency problem of PRVR methods, this paper proposes GMMFormer, a Gaussian-Mixture-Model based Transformer which models clip representations implicitly. During frame interactions, we incorporate Gaussian-Mixture-Model constraints to focus each frame on its adjacent frames instead of the whole video. Then generated representations will contain multi-scale clip information, achieving implicit clip modeling. In addition, PRVR methods ignore semantic differences between text queries relevant to the same video, leading to a sparse embedding space. We propose a query diverse loss to distinguish these text queries, making the embedding space more intensive and contain more semantic information. Extensive experiments on three large-scale video datasets (i.e., TVR, ActivityNet Captions, and Charades-STA) demonstrate the superiority and efficiency of GMMFormer. Code is available at \\url{https://github.com/huangmozhi9527/GMMFormer}.","url_abs":"https://arxiv.org/abs/2310.05195v2","url_pdf":"https://arxiv.org/pdf/2310.05195v2.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":"gmmformer-gaussian-mixture-model-based","repo_url":"https://github.com/huangmozhi9527/GMMFormer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"partially-relevant-video-retrieval","task_name":"Partially Relevant Video Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.05195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05195"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/huangmozhi9527/GMMFormer","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_honours":1,"unverified":4},"by_repo_kind":{"official":{"samples":6,"ran":2,"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":6,"samples":[{"code_sha256_prefix":"360694c320752c73","entry":"get_configs","repo":"huangmozhi9527/GMMFormer","repo_kind":"official","path":"src/Configs/builder.py","file_url":"https://github.com/huangmozhi9527/GMMFormer/blob/HEAD/src/Configs/builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"360694c320752c73"}},{"code_sha256_prefix":"1c17153fb5488283","entry":"mask_logits","repo":"huangmozhi9527/GMMFormer","repo_kind":"official","path":"src/Models/gmmformer/model.py","file_url":"https://github.com/huangmozhi9527/GMMFormer/blob/HEAD/src/Models/gmmformer/model.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1c17153fb5488283"}},{"code_sha256_prefix":"1f1241398f80e513","entry":"clean_str","repo":"huangmozhi9527/GMMFormer","repo_kind":"official","path":"src/Datasets/data_provider.py","file_url":"https://github.com/huangmozhi9527/GMMFormer/blob/HEAD/src/Datasets/data_provider.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1f1241398f80e513"}},{"code_sha256_prefix":"8c68bbddd5e8e5bc","entry":"getVideoId","repo":"huangmozhi9527/GMMFormer","repo_kind":"official","path":"src/Datasets/data_provider.py","file_url":"https://github.com/huangmozhi9527/GMMFormer/blob/HEAD/src/Datasets/data_provider.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8c68bbddd5e8e5bc"}},{"code_sha256_prefix":"23b5db90923f7386","entry":"onehot","repo":"huangmozhi9527/GMMFormer","repo_kind":"official","path":"src/Models/gmmformer/model_components.py","file_url":"https://github.com/huangmozhi9527/GMMFormer/blob/HEAD/src/Models/gmmformer/model_components.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"23b5db90923f7386"}},{"code_sha256_prefix":"70f2efad3d316afb","entry":"read_video_ids","repo":"huangmozhi9527/GMMFormer","repo_kind":"official","path":"src/Datasets/data_provider.py","file_url":"https://github.com/huangmozhi9527/GMMFormer/blob/HEAD/src/Datasets/data_provider.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"70f2efad3d316afb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}