{"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/an-image-classifier-can-suffice-video","title":"Can An Image Classifier Suffice For Action Recognition?","arxiv_id":"2106.14104","date":"2021-06-26","proceeding":"ICLR 2022 4","authors":["Quanfu Fan","Chun-Fu","Chen","Rameswar Panda"],"abstract":"We explore a new perspective on video understanding by casting the video recognition problem as an image recognition task. Our approach rearranges input video frames into super images, which allow for training an image classifier directly to fulfill the task of action recognition, in exactly the same way as image classification. With such a simple idea, we show that transformer-based image classifiers alone can suffice for action recognition. In particular, our approach demonstrates strong and promising performance against SOTA methods on several public datasets including Kinetics400, Moments In Time, Something-Something V2 (SSV2), Jester and Diving48. We also experiment with the prevalent ResNet image classifiers in computer vision to further validate our idea. The results on both Kinetics400 and SSV2 are comparable to some of the best-performed CNN approaches based on spatio-temporal modeling. Our source codes and models are available at https://github.com/IBM/sifar-pytorch.","url_abs":"https://arxiv.org/abs/2106.14104v3","url_pdf":"https://arxiv.org/pdf/2106.14104v3.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":"an-image-classifier-can-suffice-video","repo_url":"https://github.com/ibm/sifar-pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"video-recognition","task_name":"Video Recognition"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.14104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14104"}},"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/ibm/sifar-pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":2,"ran":2,"unverified":7},"by_repo_kind":{"official":{"samples":12,"ran":5,"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":"144d10b49baeb8a6","entry":"window_partition","repo":"ibm/sifar-pytorch","repo_kind":"official","path":"my_models/sifar_swin.py","file_url":"https://github.com/ibm/sifar-pytorch/blob/HEAD/my_models/sifar_swin.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"144d10b49baeb8a6"}},{"code_sha256_prefix":"2b5d65dc96c1a03b","entry":"all_gather","repo":"ibm/sifar-pytorch","repo_kind":"official","path":"simclr.py","file_url":"https://github.com/ibm/sifar-pytorch/blob/HEAD/simclr.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2b5d65dc96c1a03b"}},{"code_sha256_prefix":"8a9bb6e2787fae25","entry":"concat_all_gather","repo":"ibm/sifar-pytorch","repo_kind":"official","path":"engine.py","file_url":"https://github.com/ibm/sifar-pytorch/blob/HEAD/engine.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8a9bb6e2787fae25"}},{"code_sha256_prefix":"d4d43ca38bd196b3","entry":"load_image","repo":"ibm/sifar-pytorch","repo_kind":"official","path":"video_dataset.py","file_url":"https://github.com/ibm/sifar-pytorch/blob/HEAD/video_dataset.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d4d43ca38bd196b3"}},{"code_sha256_prefix":"61bf152e6a42a184","entry":"window_reverse","repo":"ibm/sifar-pytorch","repo_kind":"official","path":"my_models/sifar_swin.py","file_url":"https://github.com/ibm/sifar-pytorch/blob/HEAD/my_models/sifar_swin.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"61bf152e6a42a184"}},{"code_sha256_prefix":"28154a33c7d515b4","entry":"compute_img_diff","repo":"ibm/sifar-pytorch","repo_kind":"official","path":"video_dataset.py","file_url":"https://github.com/ibm/sifar-pytorch/blob/HEAD/video_dataset.py","link_basis":"plan_row","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":"28154a33c7d515b4"}},{"code_sha256_prefix":"feb6e531da1634d0","entry":"create_new_image_size","repo":"ibm/sifar-pytorch","repo_kind":"official","path":"my_models/sifar_swin.py","file_url":"https://github.com/ibm/sifar-pytorch/blob/HEAD/my_models/sifar_swin.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":"feb6e531da1634d0"}},{"code_sha256_prefix":"86ba8935921dc67e","entry":"create_super_img","repo":"ibm/sifar-pytorch","repo_kind":"official","path":"my_models/sifar_util.py","file_url":"https://github.com/ibm/sifar-pytorch/blob/HEAD/my_models/sifar_util.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":"86ba8935921dc67e"}},{"code_sha256_prefix":"e4c2355f56ef1d95","entry":"frames_to_super_image","repo":"ibm/sifar-pytorch","repo_kind":"official","path":"my_models/sifar_util.py","file_url":"https://github.com/ibm/sifar-pytorch/blob/HEAD/my_models/sifar_util.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":"e4c2355f56ef1d95"}},{"code_sha256_prefix":"52a11ad211e62513","entry":"random_clip","repo":"ibm/sifar-pytorch","repo_kind":"official","path":"video_dataset.py","file_url":"https://github.com/ibm/sifar-pytorch/blob/HEAD/video_dataset.py","link_basis":"plan_row","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":"52a11ad211e62513"}},{"code_sha256_prefix":"c5b12f7ac8a2a627","entry":"summary","repo":"ibm/sifar-pytorch","repo_kind":"official","path":"benchmark.py","file_url":"https://github.com/ibm/sifar-pytorch/blob/HEAD/benchmark.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":"c5b12f7ac8a2a627"}},{"code_sha256_prefix":"6d5c67058b4d0cf9","entry":"super_image_to_frames","repo":"ibm/sifar-pytorch","repo_kind":"official","path":"my_models/sifar_util.py","file_url":"https://github.com/ibm/sifar-pytorch/blob/HEAD/my_models/sifar_util.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":"6d5c67058b4d0cf9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}