{"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/coca-contrastive-captioners-are-image-text","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","arxiv_id":"2205.01917","date":"2022-05-04","proceeding":null,"authors":["Jiahui Yu","ZiRui Wang","Vijay Vasudevan","Legg Yeung","Mojtaba Seyedhosseini","Yonghui Wu"],"abstract":"Exploring large-scale pretrained foundation models is of significant interest in computer vision because these models can be quickly transferred to many downstream tasks. This paper presents Contrastive Captioner (CoCa), a minimalist design to pretrain an image-text encoder-decoder foundation model jointly with contrastive loss and captioning loss, thereby subsuming model capabilities from contrastive approaches like CLIP and generative methods like SimVLM. In contrast to standard encoder-decoder transformers where all decoder layers attend to encoder outputs, CoCa omits cross-attention in the first half of decoder layers to encode unimodal text representations, and cascades the remaining decoder layers which cross-attend to the image encoder for multimodal image-text representations. We apply a contrastive loss between unimodal image and text embeddings, in addition to a captioning loss on the multimodal decoder outputs which predicts text tokens autoregressively. By sharing the same computational graph, the two training objectives are computed efficiently with minimal overhead. CoCa is pretrained end-to-end and from scratch on both web-scale alt-text data and annotated images by treating all labels simply as text, seamlessly unifying natural language supervision for representation learning. Empirically, CoCa achieves state-of-the-art performance with zero-shot transfer or minimal task-specific adaptation on a broad range of downstream tasks, spanning visual recognition (ImageNet, Kinetics-400/600/700, Moments-in-Time), crossmodal retrieval (MSCOCO, Flickr30K, MSR-VTT), multimodal understanding (VQA, SNLI-VE, NLVR2), and image captioning (MSCOCO, NoCaps). Notably on ImageNet classification, CoCa obtains 86.3% zero-shot top-1 accuracy, 90.6% with a frozen encoder and learned classification head, and new state-of-the-art 91.0% top-1 accuracy on ImageNet with a finetuned encoder.","url_abs":"https://arxiv.org/abs/2205.01917v2","url_pdf":"https://arxiv.org/pdf/2205.01917v2.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":"coca-contrastive-captioners-are-image-text","repo_url":"https://github.com/Chaolei98/FreeZAD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"coca-contrastive-captioners-are-image-text","repo_url":"https://github.com/amitakamath/hard_positives","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"coca-contrastive-captioners-are-image-text","repo_url":"https://github.com/amitakamath/whatsup_vlms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"coca-contrastive-captioners-are-image-text","repo_url":"https://github.com/facebookresearch/multimodal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"coca-contrastive-captioners-are-image-text","repo_url":"https://github.com/lucidrains/CoCa-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"coca-contrastive-captioners-are-image-text","repo_url":"https://github.com/mlfoundations/open_clip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"},{"task_slug":"visual-entailment","task_name":"Visual Entailment"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"},{"task_slug":"zero-shot-cross-modal-retrieval","task_name":"Zero-Shot Cross-Modal Retrieval"},{"task_slug":"zero-shot-transfer-image-classification","task_name":"Zero-Shot Transfer Image Classification"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"simvlm","method_name":"SimVLM"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"CoCa (finetuned)","rank_in_archive_order":20,"of":207,"metrics":{"Acc@1":"88.9"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"CoCa (frozen)","rank_in_archive_order":28,"of":207,"metrics":{"Acc@1":"88.0"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-600","task":"Action Classification","dataset":"Kinetics-600","model":"CoCa (finetuned)","rank_in_archive_order":16,"of":65,"metrics":{"Top-1 Accuracy":"89.4"},"uses_additional_data":true},{"leaderboard":"/sota/action-classification-on-kinetics-600","task":"Action Classification","dataset":"Kinetics-600","model":"CoCa (frozen)","rank_in_archive_order":19,"of":65,"metrics":{"Top-1 Accuracy":"88.5"},"uses_additional_data":true},{"leaderboard":"/sota/action-classification-on-kinetics-700","task":"Action Classification","dataset":"Kinetics-700","model":"CoCa (finetuned)","rank_in_archive_order":9,"of":36,"metrics":{"Top-1 Accuracy":"82.7"},"uses_additional_data":true},{"leaderboard":"/sota/action-classification-on-kinetics-700","task":"Action Classification","dataset":"Kinetics-700","model":"CoCa (frozen)","rank_in_archive_order":10,"of":36,"metrics":{"Top-1 Accuracy":"81.1"},"uses_additional_data":true},{"leaderboard":"/sota/action-classification-on-moments-in-time-2","task":"Action Classification","dataset":"Moments in Time","model":"CoCa (finetuned)","rank_in_archive_order":3,"of":4,"metrics":{"Top 1 Accuracy":"49.0"},"uses_additional_data":true},{"leaderboard":"/sota/action-classification-on-moments-in-time-2","task":"Action Classification","dataset":"Moments in Time","model":"CoCa (frozen)","rank_in_archive_order":4,"of":4,"metrics":{"Top 1 Accuracy":"47.4"},"uses_additional_data":true},{"leaderboard":"/sota/image-captioning-on-coco-captions","task":"Image Captioning","dataset":"COCO Captions","model":"CoCa","rank_in_archive_order":16,"of":41,"metrics":{"BLEU-4":"40.9","CIDER":"143.6","METEOR":"33.9","SPICE":"24.7"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CoCa (finetuned)","rank_in_archive_order":1,"of":1060,"metrics":{"Number of params":"2100M","Top 1 Accuracy":"91.0%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"CoCa","rank_in_archive_order":1,"of":106,"metrics":{"Top-1 Accuracy":"82.7"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-msr-vtt","task":"Video Retrieval","dataset":"MSR-VTT","model":"CoCa (zero-shot)","rank_in_archive_order":25,"of":40,"metrics":{"text-to-video R@1":"30.0","text-to-video R@10":"61.6","text-to-video R@5":"52.4","video-to-text R@1":"49.9","video-to-text R@10":"81.4","video-to-text R@5":"73.4"},"uses_additional_data":true},{"leaderboard":"/sota/visual-entailment-on-snli-ve-test","task":"Visual Entailment","dataset":"SNLI-VE test","model":"CoCa","rank_in_archive_order":3,"of":8,"metrics":{"Accuracy":"87.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-entailment-on-snli-ve-val","task":"Visual Entailment","dataset":"SNLI-VE val","model":"CoCa","rank_in_archive_order":3,"of":9,"metrics":{"Accuracy":"87.0"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev-1","task":"Visual Question Answering","dataset":"VQA v2 test-dev","model":"CoCa","rank_in_archive_order":2,"of":11,"metrics":{"Accuracy":"82.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-nlvr2-dev","task":"Visual Reasoning","dataset":"NLVR2 Dev","model":"CoCa","rank_in_archive_order":5,"of":15,"metrics":{"Accuracy":"86.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-nlvr2-test","task":"Visual Reasoning","dataset":"NLVR2 Test","model":"CoCa","rank_in_archive_order":4,"of":14,"metrics":{"Accuracy":"87.0"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-cross-modal-retrieval-on-coco-2014","task":"Zero-Shot Cross-Modal Retrieval","dataset":"COCO 2014","model":"CoCa","rank_in_archive_order":9,"of":18,"metrics":{"Image-to-text R@1":"66.3","Image-to-text R@10":"91.8","Image-to-text R@5":"86.2","Text-to-image R@1":"51.2","Text-to-image R@10":"82.0","Text-to-image R@5":"74.2"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-cross-modal-retrieval-on-flickr30k","task":"Zero-Shot Cross-Modal Retrieval","dataset":"Flickr30k","model":"CoCa","rank_in_archive_order":5,"of":22,"metrics":{"Image-to-text R@1":"92.5","Image-to-text R@10":"99.9","Image-to-text R@5":"99.5","Text-to-image R@1":"80.4","Text-to-image R@10":"97.7","Text-to-image R@5":"95.7"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-1","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet","model":"CoCa","rank_in_archive_order":3,"of":23,"metrics":{"Accuracy (Private)":"86.3"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-3","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet V2","model":"CoCa","rank_in_archive_order":3,"of":13,"metrics":{"Accuracy (Private)":"80.7"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-5","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet-A","model":"CoCa","rank_in_archive_order":1,"of":13,"metrics":{"Accuracy (Private)":"90.2"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-4","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet-R","model":"CoCa","rank_in_archive_order":2,"of":12,"metrics":{"Accuracy":"96.5"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-8","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet-Sketch","model":"CoCa","rank_in_archive_order":1,"of":7,"metrics":{"Accuracy (Private)":"77.6"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-6","task":"Zero-Shot Transfer Image Classification","dataset":"ObjectNet","model":"CoCa","rank_in_archive_order":3,"of":9,"metrics":{"Accuracy (Private)":"82.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.01917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01917"}},"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/mlfoundations/open_clip","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/amitakamath/whatsup_vlms","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/CoCa-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Chaolei98/FreeZAD","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/amitakamath/hard_positives","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/multimodal","reach":null}],"summary":{"ran":7,"ran_honours":2,"unverified":8},"by_repo_kind":{"listed":{"samples":17,"ran":9,"repositories":2}},"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":"38c836510c2b097d","entry":"CoCaTextEmbeddings","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/coca/coca_model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/coca/coca_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"38c836510c2b097d"}},{"code_sha256_prefix":"1851c02d87765a1f","entry":"Fp32LayerNorm","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/coca/coca_model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/coca/coca_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"1851c02d87765a1f"}},{"code_sha256_prefix":"c3bf9823eb334b94","entry":"MHAWithCacheOutput","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/coca/coca_model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/coca/coca_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c3bf9823eb334b94"}},{"code_sha256_prefix":"69bbd7902f886836","entry":"MLP","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/coca/coca_model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/coca/coca_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"69bbd7902f886836"}},{"code_sha256_prefix":"c48e25a9b1ad8b20","entry":"MultimodalOutput","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/coca/coca_model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/coca/coca_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c48e25a9b1ad8b20"}},{"code_sha256_prefix":"16907aa066126740","entry":"TransformerOutput","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/coca/coca_model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/coca/coca_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"16907aa066126740"}},{"code_sha256_prefix":"e35be5f71f1604be","entry":"get_causal_attention_mask","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/coca/coca_model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/coca/coca_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e35be5f71f1604be"}},{"code_sha256_prefix":"1fc3d3455e5edcbb","entry":"interpolated_prec_rec","repo":"Chaolei98/FreeZAD","repo_kind":"listed","path":"evaluate.py","file_url":"https://github.com/Chaolei98/FreeZAD/blob/HEAD/evaluate.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":"1fc3d3455e5edcbb"}},{"code_sha256_prefix":"d0744a2fe3151508","entry":"segment_iou","repo":"Chaolei98/FreeZAD","repo_kind":"listed","path":"evaluate.py","file_url":"https://github.com/Chaolei98/FreeZAD/blob/HEAD/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d0744a2fe3151508"}},{"code_sha256_prefix":"c3f20e8434033e06","entry":"CoCaModel","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/coca/coca_model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/coca/coca_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c3f20e8434033e06"}},{"code_sha256_prefix":"d39521c69dad724c","entry":"CoCaMultimodalDecoder","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/coca/coca_model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/coca/coca_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d39521c69dad724c"}},{"code_sha256_prefix":"378d7fee25d36766","entry":"CoCaTextDecoder","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/coca/coca_model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/coca/coca_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"378d7fee25d36766"}},{"code_sha256_prefix":"a73d62315a5ca5ca","entry":"MultiHeadAttentionWithCache","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/coca/coca_model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/coca/coca_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a73d62315a5ca5ca"}},{"code_sha256_prefix":"a241668983092d20","entry":"TransformerDecoder","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/coca/coca_model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/coca/coca_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a241668983092d20"}},{"code_sha256_prefix":"3624eeb428e322e8","entry":"TransformerDecoderLayer","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/coca/coca_model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/coca/coca_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"3624eeb428e322e8"}},{"code_sha256_prefix":"320499e20591d89f","entry":"compute_average_precision_detection","repo":"Chaolei98/FreeZAD","repo_kind":"listed","path":"evaluate.py","file_url":"https://github.com/Chaolei98/FreeZAD/blob/HEAD/evaluate.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":"320499e20591d89f"}},{"code_sha256_prefix":"f6224c8305205872","entry":"get_video_info","repo":"Chaolei98/FreeZAD","repo_kind":"listed","path":"extract_features.py","file_url":"https://github.com/Chaolei98/FreeZAD/blob/HEAD/extract_features.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":"f6224c8305205872"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}