{"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/ct-net-channel-tensorization-network-for-1","title":"CT-Net: Channel Tensorization Network for Video Classification","arxiv_id":"2106.01603","date":"2021-06-03","proceeding":"ICLR 2021 1","authors":["Kunchang Li","Xianhang Li","Yali Wang","Jun Wang","Yu Qiao"],"abstract":"3D convolution is powerful for video classification but often computationally expensive, recent studies mainly focus on decomposing it on spatial-temporal and/or channel dimensions. Unfortunately, most approaches fail to achieve a preferable balance between convolutional efficiency and feature-interaction sufficiency. For this reason, we propose a concise and novel Channel Tensorization Network (CT-Net), by treating the channel dimension of input feature as a multiplication of K sub-dimensions. On one hand, it naturally factorizes convolution in a multiple dimension way, leading to a light computation burden. On the other hand, it can effectively enhance feature interaction from different channels, and progressively enlarge the 3D receptive field of such interaction to boost classification accuracy. Furthermore, we equip our CT-Module with a Tensor Excitation (TE) mechanism. It can learn to exploit spatial, temporal and channel attention in a high-dimensional manner, to improve the cooperative power of all the feature dimensions in our CT-Module. Finally, we flexibly adapt ResNet as our CT-Net. Extensive experiments are conducted on several challenging video benchmarks, e.g., Kinetics-400, Something-Something V1 and V2. Our CT-Net outperforms a number of recent SOTA approaches, in terms of accuracy and/or efficiency. The codes and models will be available on https://github.com/Andy1621/CT-Net.","url_abs":"https://arxiv.org/abs/2106.01603v1","url_pdf":"https://arxiv.org/pdf/2106.01603v1.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":"ct-net-channel-tensorization-network-for-1","repo_url":"https://github.com/Andy1621/CT-Net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"video-classification","task_name":"Video 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":[{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"CT-Net Ensemble","rank_in_archive_order":106,"of":207,"metrics":{"Acc@1":"79.8"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something-1","task":"Action Recognition","dataset":"Something-Something V1","model":"CT-Net Ensemble (R50, 8+12+16+24)","rank_in_archive_order":20,"of":74,"metrics":{"Top 1 Accuracy":"56.6"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something","task":"Action Recognition","dataset":"Something-Something V2","model":"CT-Net Ensemble (R50, 8+12+16+24)","rank_in_archive_order":59,"of":123,"metrics":{"GFLOPs":"280","Parameters":"83.8","Top-1 Accuracy":"67.8","Top-5 Accuracy":"91.1"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.01603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01603"}},"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":"deterministic:regex_extraction","url":"https://github.com/Andy1621/CT-Net","reach":null}],"summary":{"ran":2,"ran_draft_wrong":7,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":13,"ran":10,"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":"6260211e3787baa5","entry":"ChannelGroupAttention","repo":"Andy1621/CT-Net","repo_kind":"official","path":"ops/reshape_block.py","file_url":"https://github.com/Andy1621/CT-Net/blob/HEAD/ops/reshape_block.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6260211e3787baa5"}},{"code_sha256_prefix":"aee433c108b8ad52","entry":"TemporalGroupAttention","repo":"Andy1621/CT-Net","repo_kind":"official","path":"ops/reshape_block.py","file_url":"https://github.com/Andy1621/CT-Net/blob/HEAD/ops/reshape_block.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aee433c108b8ad52"}},{"code_sha256_prefix":"c455a6669e2554a5","entry":"conv_1x1_bn","repo":"Andy1621/CT-Net","repo_kind":"official","path":"ops/reshape_block.py","file_url":"https://github.com/Andy1621/CT-Net/blob/HEAD/ops/reshape_block.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c455a6669e2554a5"}},{"code_sha256_prefix":"ec968a25ec7aef0f","entry":"conv_1x1x1","repo":"Andy1621/CT-Net","repo_kind":"official","path":"ops/reshape_block.py","file_url":"https://github.com/Andy1621/CT-Net/blob/HEAD/ops/reshape_block.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec968a25ec7aef0f"}},{"code_sha256_prefix":"c2f0baed989321b4","entry":"conv_1x1x1_bn","repo":"Andy1621/CT-Net","repo_kind":"official","path":"ops/reshape_block.py","file_url":"https://github.com/Andy1621/CT-Net/blob/HEAD/ops/reshape_block.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c2f0baed989321b4"}},{"code_sha256_prefix":"537b6a478a291bb6","entry":"conv_1x3x3","repo":"Andy1621/CT-Net","repo_kind":"official","path":"ops/reshape_block.py","file_url":"https://github.com/Andy1621/CT-Net/blob/HEAD/ops/reshape_block.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"537b6a478a291bb6"}},{"code_sha256_prefix":"ed910e0667f0eb1e","entry":"conv_1x3x3_bn","repo":"Andy1621/CT-Net","repo_kind":"official","path":"ops/reshape_block.py","file_url":"https://github.com/Andy1621/CT-Net/blob/HEAD/ops/reshape_block.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed910e0667f0eb1e"}},{"code_sha256_prefix":"2b0d4f8ad8c45d75","entry":"conv_3x1x1","repo":"Andy1621/CT-Net","repo_kind":"official","path":"ops/reshape_block.py","file_url":"https://github.com/Andy1621/CT-Net/blob/HEAD/ops/reshape_block.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b0d4f8ad8c45d75"}},{"code_sha256_prefix":"951a6b522747450c","entry":"conv_3x1x1_bn","repo":"Andy1621/CT-Net","repo_kind":"official","path":"ops/reshape_block.py","file_url":"https://github.com/Andy1621/CT-Net/blob/HEAD/ops/reshape_block.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"951a6b522747450c"}},{"code_sha256_prefix":"ca18d92d71a013ef","entry":"get_xy","repo":"Andy1621/CT-Net","repo_kind":"official","path":"ops/reshape_block.py","file_url":"https://github.com/Andy1621/CT-Net/blob/HEAD/ops/reshape_block.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca18d92d71a013ef"}},{"code_sha256_prefix":"b66d42a805e6085e","entry":"ReshapeBlock","repo":"Andy1621/CT-Net","repo_kind":"official","path":"ops/reshape_block.py","file_url":"https://github.com/Andy1621/CT-Net/blob/HEAD/ops/reshape_block.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":"b66d42a805e6085e"}},{"code_sha256_prefix":"9d7ca7fd0b4939d3","entry":"ReshapeInteraction","repo":"Andy1621/CT-Net","repo_kind":"official","path":"ops/reshape_block.py","file_url":"https://github.com/Andy1621/CT-Net/blob/HEAD/ops/reshape_block.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":"9d7ca7fd0b4939d3"}},{"code_sha256_prefix":"6bcaa5143e16e1ab","entry":"SpatialGroupAttention","repo":"Andy1621/CT-Net","repo_kind":"official","path":"ops/reshape_block.py","file_url":"https://github.com/Andy1621/CT-Net/blob/HEAD/ops/reshape_block.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":"6bcaa5143e16e1ab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}