{"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/rethinking-zero-shot-video-classification-end","title":"Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications","arxiv_id":"2003.01455","date":"2020-03-03","proceeding":"CVPR 2020 6","authors":["Biagio Brattoli","Joseph Tighe","Fedor Zhdanov","Pietro Perona","Krzysztof Chalupka"],"abstract":"Trained on large datasets, deep learning (DL) can accurately classify videos into hundreds of diverse classes. However, video data is expensive to annotate. Zero-shot learning (ZSL) proposes one solution to this problem. ZSL trains a model once, and generalizes to new tasks whose classes are not present in the training dataset. We propose the first end-to-end algorithm for ZSL in video classification. Our training procedure builds on insights from recent video classification literature and uses a trainable 3D CNN to learn the visual features. This is in contrast to previous video ZSL methods, which use pretrained feature extractors. We also extend the current benchmarking paradigm: Previous techniques aim to make the test task unknown at training time but fall short of this goal. We encourage domain shift across training and test data and disallow tailoring a ZSL model to a specific test dataset. We outperform the state-of-the-art by a wide margin. Our code, evaluation procedure and model weights are available at github.com/bbrattoli/ZeroShotVideoClassification.","url_abs":"https://arxiv.org/abs/2003.01455v4","url_pdf":"https://arxiv.org/pdf/2003.01455v4.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":"rethinking-zero-shot-video-classification-end","repo_url":"https://github.com/bbrattoli/ZeroShotVideoClassification","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"video-classification","task_name":"Video Classification"},{"task_slug":"zero-shot-action-recognition","task_name":"Zero-Shot Action Recognition"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-action-recognition-on-activitynet","task":"Zero-Shot Action Recognition","dataset":"ActivityNet","model":"E2E","rank_in_archive_order":5,"of":5,"metrics":{"Top-1 Accuracy":"26.6"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-action-recognition-on-hmdb51","task":"Zero-Shot Action Recognition","dataset":"HMDB51","model":"E2E","rank_in_archive_order":20,"of":29,"metrics":{"Top-1 Accuracy":"32.7"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-action-recognition-on-ucf101","task":"Zero-Shot Action Recognition","dataset":"UCF101","model":"E2E","rank_in_archive_order":21,"of":35,"metrics":{"Top-1 Accuracy":"48"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.01455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.01455"}},"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/bbrattoli/ZeroShotVideoClassification","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":12},"by_repo_kind":{"official":{"samples":12,"ran":0,"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":"531f342bc7e75870","entry":"bottom_right_crop","repo":"bbrattoli/ZeroShotVideoClassification","repo_kind":"official","path":"auxiliary/transforms.py","file_url":"https://github.com/bbrattoli/ZeroShotVideoClassification/blob/HEAD/auxiliary/transforms.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"531f342bc7e75870"}},{"code_sha256_prefix":"02f1d05c80b05b15","entry":"classes2embedding","repo":"bbrattoli/ZeroShotVideoClassification","repo_kind":"official","path":"auxiliary/auxiliary_word2vec.py","file_url":"https://github.com/bbrattoli/ZeroShotVideoClassification/blob/HEAD/auxiliary/auxiliary_word2vec.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"02f1d05c80b05b15"}},{"code_sha256_prefix":"793e9066bced287c","entry":"filter_classes","repo":"bbrattoli/ZeroShotVideoClassification","repo_kind":"official","path":"auxiliary/auxiliary_dataset.py","file_url":"https://github.com/bbrattoli/ZeroShotVideoClassification/blob/HEAD/auxiliary/auxiliary_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"793e9066bced287c"}},{"code_sha256_prefix":"759eae90406d1197","entry":"filter_samples","repo":"bbrattoli/ZeroShotVideoClassification","repo_kind":"official","path":"auxiliary/auxiliary_dataset.py","file_url":"https://github.com/bbrattoli/ZeroShotVideoClassification/blob/HEAD/auxiliary/auxiliary_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"759eae90406d1197"}},{"code_sha256_prefix":"41c8dda152073129","entry":"get_kinetics","repo":"bbrattoli/ZeroShotVideoClassification","repo_kind":"official","path":"auxiliary/auxiliary_dataset.py","file_url":"https://github.com/bbrattoli/ZeroShotVideoClassification/blob/HEAD/auxiliary/auxiliary_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"41c8dda152073129"}},{"code_sha256_prefix":"b0870d87b60ff48d","entry":"get_network","repo":"bbrattoli/ZeroShotVideoClassification","repo_kind":"official","path":"network.py","file_url":"https://github.com/bbrattoli/ZeroShotVideoClassification/blob/HEAD/network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b0870d87b60ff48d"}},{"code_sha256_prefix":"c9ac10e3edc10ca2","entry":"load_clips_npy","repo":"bbrattoli/ZeroShotVideoClassification","repo_kind":"official","path":"auxiliary/auxiliary_activitynet.py","file_url":"https://github.com/bbrattoli/ZeroShotVideoClassification/blob/HEAD/auxiliary/auxiliary_activitynet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c9ac10e3edc10ca2"}},{"code_sha256_prefix":"977b7bd5c50996b1","entry":"one_class2embed_hmdb","repo":"bbrattoli/ZeroShotVideoClassification","repo_kind":"official","path":"auxiliary/auxiliary_word2vec.py","file_url":"https://github.com/bbrattoli/ZeroShotVideoClassification/blob/HEAD/auxiliary/auxiliary_word2vec.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"977b7bd5c50996b1"}},{"code_sha256_prefix":"a75706c4fd477de4","entry":"one_class2embed_ucf","repo":"bbrattoli/ZeroShotVideoClassification","repo_kind":"official","path":"auxiliary/auxiliary_word2vec.py","file_url":"https://github.com/bbrattoli/ZeroShotVideoClassification/blob/HEAD/auxiliary/auxiliary_word2vec.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a75706c4fd477de4"}},{"code_sha256_prefix":"f26f8a6525ee907c","entry":"resize_video","repo":"bbrattoli/ZeroShotVideoClassification","repo_kind":"official","path":"auxiliary/auxiliary_activitynet.py","file_url":"https://github.com/bbrattoli/ZeroShotVideoClassification/blob/HEAD/auxiliary/auxiliary_activitynet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f26f8a6525ee907c"}},{"code_sha256_prefix":"71f94cc2cc42b445","entry":"top_left_crop","repo":"bbrattoli/ZeroShotVideoClassification","repo_kind":"official","path":"auxiliary/transforms.py","file_url":"https://github.com/bbrattoli/ZeroShotVideoClassification/blob/HEAD/auxiliary/transforms.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"71f94cc2cc42b445"}},{"code_sha256_prefix":"7278c7363f119bd3","entry":"top_right_crop","repo":"bbrattoli/ZeroShotVideoClassification","repo_kind":"official","path":"auxiliary/transforms.py","file_url":"https://github.com/bbrattoli/ZeroShotVideoClassification/blob/HEAD/auxiliary/transforms.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7278c7363f119bd3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}