{"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/ptseformer-progressive-temporal-spatial","title":"PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer Towards Video Object Detection","arxiv_id":"2209.02242","date":"2022-09-06","proceeding":null,"authors":["Han Wang","Jun Tang","Xiaodong Liu","Shanyan Guan","Rong Xie","Li Song"],"abstract":"Recent years have witnessed a trend of applying context frames to boost the performance of object detection as video object detection. Existing methods usually aggregate features at one stroke to enhance the feature. These methods, however, usually lack spatial information from neighboring frames and suffer from insufficient feature aggregation. To address the issues, we perform a progressive way to introduce both temporal information and spatial information for an integrated enhancement. The temporal information is introduced by the temporal feature aggregation model (TFAM), by conducting an attention mechanism between the context frames and the target frame (i.e., the frame to be detected). Meanwhile, we employ a Spatial Transition Awareness Model (STAM) to convey the location transition information between each context frame and target frame. Built upon a transformer-based detector DETR, our PTSEFormer also follows an end-to-end fashion to avoid heavy post-processing procedures while achieving 88.1% mAP on the ImageNet VID dataset. Codes are available at https://github.com/Hon-Wong/PTSEFormer.","url_abs":"https://arxiv.org/abs/2209.02242v1","url_pdf":"https://arxiv.org/pdf/2209.02242v1.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":"ptseformer-progressive-temporal-spatial","repo_url":"https://github.com/hon-wong/ptseformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"video-object-detection","task_name":"Video Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-object-detection-on-imagenet-vid","task":"Video Object Detection","dataset":"ImageNet VID","model":"PTSEFormer (ResNet-101)","rank_in_archive_order":7,"of":33,"metrics":{"MAP ":"88.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.02242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.02242"}},"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/Hon-Wong/PTSEFormer","reach":null}],"summary":{"ran":13,"ran_draft_wrong":1,"unverified":7},"by_repo_kind":{"official":{"samples":21,"ran":14,"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":"63d4c9530be04f79","entry":"BackboneBase","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"63d4c9530be04f79"}},{"code_sha256_prefix":"ab5760a4f1f38dd2","entry":"DeformableTransformerDecoder","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.py","link_basis":"first_harvest_node","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":"ab5760a4f1f38dd2"}},{"code_sha256_prefix":"a074eb87991640c4","entry":"DeformableTransformerEncoder","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a074eb87991640c4"}},{"code_sha256_prefix":"83acef54aa936437","entry":"FrozenBatchNorm2d","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"83acef54aa936437"}},{"code_sha256_prefix":"72ab0aab987d0596","entry":"Joiner","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"72ab0aab987d0596"}},{"code_sha256_prefix":"a3406c64394db6f0","entry":"LSTMLikeSENet","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.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":"a3406c64394db6f0"}},{"code_sha256_prefix":"fd3c89afd641c536","entry":"MSDeformAttn","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd3c89afd641c536"}},{"code_sha256_prefix":"bea736025771555d","entry":"OursDecoderLayerV2","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bea736025771555d"}},{"code_sha256_prefix":"f1e72b80021df791","entry":"OursDecoderV2","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f1e72b80021df791"}},{"code_sha256_prefix":"2e16cdcea17dfdc0","entry":"PositionEmbeddingLearned","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e16cdcea17dfdc0"}},{"code_sha256_prefix":"747992503b5e8c6b","entry":"PositionEmbeddingSine","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"747992503b5e8c6b"}},{"code_sha256_prefix":"5c57a6a5e5ed847a","entry":"SimpleDecoderLayerV2","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c57a6a5e5ed847a"}},{"code_sha256_prefix":"91c2043c0d5cc3fb","entry":"SimpleDecoderV2","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"91c2043c0d5cc3fb"}},{"code_sha256_prefix":"f2cdbc05e138fb89","entry":"build_position_encoding","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f2cdbc05e138fb89"}},{"code_sha256_prefix":"a211f6c6ab02ec90","entry":"Backbone","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.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":"a211f6c6ab02ec90"}},{"code_sha256_prefix":"b9c992339536b95b","entry":"DeformableTransformerDecoderLayer","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.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":"b9c992339536b95b"}},{"code_sha256_prefix":"4b89372abf4189ba","entry":"DeformableTransformerEncoderLayer","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.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":"4b89372abf4189ba"}},{"code_sha256_prefix":"b14eec9093b96e6d","entry":"PTSEFormer","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.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":"b14eec9093b96e6d"}},{"code_sha256_prefix":"008eda08de0fc359","entry":"build_backbone","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.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":"008eda08de0fc359"}},{"code_sha256_prefix":"952247bf85e628c6","entry":"build_deformable_decoder","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.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":"952247bf85e628c6"}},{"code_sha256_prefix":"0e29dbaab3fc21bc","entry":"build_deformable_encoder","repo":"Hon-Wong/PTSEFormer","repo_kind":"official","path":"src/models/model_builder.py","file_url":"https://github.com/Hon-Wong/PTSEFormer/blob/HEAD/src/models/model_builder.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":"0e29dbaab3fc21bc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}