{"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/depth-guided-adaptive-meta-fusion-network-for","title":"Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition","arxiv_id":"2010.09982","date":"2020-10-20","proceeding":null,"authors":["Yuqian Fu","Li Zhang","Junke Wang","Yanwei Fu","Yu-Gang Jiang"],"abstract":"Humans can easily recognize actions with only a few examples given, while the existing video recognition models still heavily rely on the large-scale labeled data inputs. This observation has motivated an increasing interest in few-shot video action recognition, which aims at learning new actions with only very few labeled samples. In this paper, we propose a depth guided Adaptive Meta-Fusion Network for few-shot video recognition which is termed as AMeFu-Net. Concretely, we tackle the few-shot recognition problem from three aspects: firstly, we alleviate this extremely data-scarce problem by introducing depth information as a carrier of the scene, which will bring extra visual information to our model; secondly, we fuse the representation of original RGB clips with multiple non-strictly corresponding depth clips sampled by our temporal asynchronization augmentation mechanism, which synthesizes new instances at feature-level; thirdly, a novel Depth Guided Adaptive Instance Normalization (DGAdaIN) fusion module is proposed to fuse the two-stream modalities efficiently. Additionally, to better mimic the few-shot recognition process, our model is trained in the meta-learning way. Extensive experiments on several action recognition benchmarks demonstrate the effectiveness of our model.","url_abs":"https://arxiv.org/abs/2010.09982v1","url_pdf":"https://arxiv.org/pdf/2010.09982v1.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":"depth-guided-adaptive-meta-fusion-network-for","repo_url":"https://github.com/lovelyqian/AMeFu-Net","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"few-shot-action-recognition","task_name":"Few Shot Action Recognition"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"video-recognition","task_name":"Video Recognition"}],"methods":[{"method_slug":"adaptive-instance-normalization","method_name":"Adaptive Instance Normalization"},{"method_slug":"instance-normalization","method_name":"Instance Normalization"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-action-recognition-on-hmdb51","task":"Few Shot Action Recognition","dataset":"HMDB51","model":"AMeFu-Net","rank_in_archive_order":5,"of":7,"metrics":{"1:1 Accuracy":"75.5"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-action-recognition-on-kinetics-100","task":"Few Shot Action Recognition","dataset":"Kinetics-100","model":"AMeFu-Net","rank_in_archive_order":2,"of":8,"metrics":{"Accuracy":"86.8"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-action-recognition-on-ucf101","task":"Few Shot Action Recognition","dataset":"UCF101","model":"AMeFu-Net","rank_in_archive_order":4,"of":7,"metrics":{"1:1 Accuracy":"95.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.09982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.09982"}},"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/lovelyqian/AMeFu-Net","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":9},"by_repo_kind":{"official":{"samples":10,"ran":1,"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":"4dd319c45d372246","entry":"euclidean_dist","repo":"lovelyqian/AMeFu-Net","repo_kind":"official","path":"classifier_with_loss.py","file_url":"https://github.com/lovelyqian/AMeFu-Net/blob/HEAD/classifier_with_loss.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4dd319c45d372246"}},{"code_sha256_prefix":"d2788db765438921","entry":"cosine_dist","repo":"lovelyqian/AMeFu-Net","repo_kind":"official","path":"classifier_with_loss.py","file_url":"https://github.com/lovelyqian/AMeFu-Net/blob/HEAD/classifier_with_loss.py","link_basis":"first_harvest_node","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":"d2788db765438921"}},{"code_sha256_prefix":"a89076818baaaeb3","entry":"generate_prototypes_tensor_lowerdim","repo":"lovelyqian/AMeFu-Net","repo_kind":"official","path":"classifier_with_loss.py","file_url":"https://github.com/lovelyqian/AMeFu-Net/blob/HEAD/classifier_with_loss.py","link_basis":"first_harvest_node","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":"a89076818baaaeb3"}},{"code_sha256_prefix":"cb2913ffa98c1d19","entry":"generate_prototypes_tensor_lowerdim","repo":"lovelyqian/AMeFu-Net","repo_kind":"official","path":"classifier.py","file_url":"https://github.com/lovelyqian/AMeFu-Net/blob/HEAD/classifier.py","link_basis":"first_harvest_node","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":"cb2913ffa98c1d19"}},{"code_sha256_prefix":"8bcd2d489feee989","entry":"generate_resized_numpy_1d_depth_list","repo":"lovelyqian/AMeFu-Net","repo_kind":"official","path":"sources/generate_depth.py","file_url":"https://github.com/lovelyqian/AMeFu-Net/blob/HEAD/sources/generate_depth.py","link_basis":"first_harvest_node","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":"8bcd2d489feee989"}},{"code_sha256_prefix":"f4fb554c535c6c73","entry":"get_video_fusion_from_video_info_rgb_depth_object","repo":"lovelyqian/AMeFu-Net","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lovelyqian/AMeFu-Net/blob/HEAD/utils.py","link_basis":"first_harvest_node","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":"f4fb554c535c6c73"}},{"code_sha256_prefix":"90269b4184e40202","entry":"get_video_fusion_from_video_info_rgb_depth_object_multi_depth","repo":"lovelyqian/AMeFu-Net","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lovelyqian/AMeFu-Net/blob/HEAD/utils.py","link_basis":"first_harvest_node","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":"90269b4184e40202"}},{"code_sha256_prefix":"e7727af6f6dd1a13","entry":"one_shot_classifier_prototype_lowerdim","repo":"lovelyqian/AMeFu-Net","repo_kind":"official","path":"classifier.py","file_url":"https://github.com/lovelyqian/AMeFu-Net/blob/HEAD/classifier.py","link_basis":"first_harvest_node","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":"e7727af6f6dd1a13"}},{"code_sha256_prefix":"adc0d39a7d675c29","entry":"parse_args","repo":"lovelyqian/AMeFu-Net","repo_kind":"official","path":"options.py","file_url":"https://github.com/lovelyqian/AMeFu-Net/blob/HEAD/options.py","link_basis":"first_harvest_node","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":"adc0d39a7d675c29"}},{"code_sha256_prefix":"de5649385b5cee5b","entry":"transforms","repo":"lovelyqian/AMeFu-Net","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lovelyqian/AMeFu-Net/blob/HEAD/utils.py","link_basis":"first_harvest_node","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":"de5649385b5cee5b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}