{"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/exploring-predicate-visual-context-in","title":"Exploring Predicate Visual Context in Detecting Human-Object Interactions","arxiv_id":"2308.06202","date":"2023-08-11","proceeding":"ICCV 2023 1","authors":["Frederic Z. Zhang","Yuhui Yuan","Dylan Campbell","Zhuoyao Zhong","Stephen Gould"],"abstract":"Recently, the DETR framework has emerged as the dominant approach for human--object interaction (HOI) research. In particular, two-stage transformer-based HOI detectors are amongst the most performant and training-efficient approaches. However, these often condition HOI classification on object features that lack fine-grained contextual information, eschewing pose and orientation information in favour of visual cues about object identity and box extremities. This naturally hinders the recognition of complex or ambiguous interactions. In this work, we study these issues through visualisations and carefully designed experiments. Accordingly, we investigate how best to re-introduce image features via cross-attention. With an improved query design, extensive exploration of keys and values, and box pair positional embeddings as spatial guidance, our model with enhanced predicate visual context (PViC) outperforms state-of-the-art methods on the HICO-DET and V-COCO benchmarks, while maintaining low training cost.","url_abs":"https://arxiv.org/abs/2308.06202v2","url_pdf":"https://arxiv.org/pdf/2308.06202v2.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":"exploring-predicate-visual-context-in","repo_url":"https://github.com/fredzzhang/pvic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"human-object-interaction-detection","task_name":"Human-Object Interaction Detection"},{"task_slug":"object","task_name":"Object"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"detr","method_name":"Detr"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/human-object-interaction-detection-on-hico","task":"Human-Object Interaction Detection","dataset":"HICO-DET","model":"PViC-SwinL","rank_in_archive_order":3,"of":55,"metrics":{"mAP":"44.32"},"uses_additional_data":false},{"leaderboard":"/sota/human-object-interaction-detection-on-hico","task":"Human-Object Interaction Detection","dataset":"HICO-DET","model":"PViC-R50","rank_in_archive_order":15,"of":55,"metrics":{"mAP":"34.69"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.06202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06202"}},"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/fredzzhang/pvic","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran":2,"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":9,"ran":3,"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":"adb27432af8317e7","entry":"compute_sinusoidal_pe","repo":"fredzzhang/pvic","repo_kind":"official","path":"ops.py","file_url":"https://github.com/fredzzhang/pvic/blob/HEAD/ops.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"adb27432af8317e7"}},{"code_sha256_prefix":"83c03ceb1307c6c4","entry":"inverse_sigmoid","repo":"fredzzhang/pvic","repo_kind":"official","path":"pvic.py","file_url":"https://github.com/fredzzhang/pvic/blob/HEAD/pvic.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"83c03ceb1307c6c4"}},{"code_sha256_prefix":"87b23887adcabf7a","entry":"prepare_region_proposals","repo":"fredzzhang/pvic","repo_kind":"official","path":"ops.py","file_url":"https://github.com/fredzzhang/pvic/blob/HEAD/ops.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":"87b23887adcabf7a"}},{"code_sha256_prefix":"b186c49427f4c57b","entry":"associate_with_ground_truth","repo":"fredzzhang/pvic","repo_kind":"official","path":"ops.py","file_url":"https://github.com/fredzzhang/pvic/blob/HEAD/ops.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":"b186c49427f4c57b"}},{"code_sha256_prefix":"8c73b8b7646a5ae4","entry":"custom_collate","repo":"fredzzhang/pvic","repo_kind":"official","path":"utils.py","file_url":"https://github.com/fredzzhang/pvic/blob/HEAD/utils.py","link_basis":"harvester_set","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":"8c73b8b7646a5ae4"}},{"code_sha256_prefix":"7653b4a0a7557b30","entry":"multi_head_attention_forward","repo":"fredzzhang/pvic","repo_kind":"official","path":"attention.py","file_url":"https://github.com/fredzzhang/pvic/blob/HEAD/attention.py","link_basis":"harvester_set","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":"7653b4a0a7557b30"}},{"code_sha256_prefix":"29395dbd34ec7691","entry":"shifted_window_attention","repo":"fredzzhang/pvic","repo_kind":"official","path":"transformers.py","file_url":"https://github.com/fredzzhang/pvic/blob/HEAD/transformers.py","link_basis":"harvester_set","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":"29395dbd34ec7691"}},{"code_sha256_prefix":"256ec3ee8631f23b","entry":"stochastic_depth","repo":"fredzzhang/pvic","repo_kind":"official","path":"transformers.py","file_url":"https://github.com/fredzzhang/pvic/blob/HEAD/transformers.py","link_basis":"harvester_set","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":"256ec3ee8631f23b"}},{"code_sha256_prefix":"b34159e5e7a7d936","entry":"test_clip","repo":"fredzzhang/pvic","repo_kind":"official","path":"attn.py","file_url":"https://github.com/fredzzhang/pvic/blob/HEAD/attn.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":"b34159e5e7a7d936"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}