Papers › Exploring Predicate Visual Context in Detecting Human-Object Interactions

Exploring Predicate Visual Context in Detecting Human-Object Interactions

11 Aug 2023ICCV 2023 1arXiv:2308.06202archive 2025-07-28

Frederic Z. Zhang, Yuhui Yuan, Dylan Campbell, Zhuoyao Zhong, Stephen Gould

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2308.06202")

Code

Syntology Ran 3 of 9 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

fredzzhang/pvic officialmentioned in papermentioned on GitHubpytorchBSD-3-Clause report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested; 3 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
2ran
6unverified

Licence: 0 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from fredzzhang/pvic. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

compute_sinusoidal_pe fredzzhang/pvic/ops.py official repository ran fingerprinted BSD-3-Clause (permissive) · adb27432af8317e7 · report
inverse_sigmoid fredzzhang/pvic/pvic.py official repository ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · 83c03ceb1307c6c4 · report
prepare_region_proposals fredzzhang/pvic/ops.py official repository ran BSD-3-Clause (permissive) · 87b23887adcabf7a · report
associate_with_ground_truth fredzzhang/pvic/ops.py official repository unverified BSD-3-Clause (permissive) · b186c49427f4c57b · report
custom_collate fredzzhang/pvic/utils.py official repository unverified BSD-3-Clause (permissive) · 8c73b8b7646a5ae4 · report
multi_head_attention_forward fredzzhang/pvic/attention.py official repository unverified BSD-3-Clause (permissive) · 7653b4a0a7557b30 · report
shifted_window_attention fredzzhang/pvic/transformers.py official repository unverified BSD-3-Clause (permissive) · 29395dbd34ec7691 · report
stochastic_depth fredzzhang/pvic/transformers.py official repository unverified BSD-3-Clause (permissive) · 256ec3ee8631f23b · report
test_clip fredzzhang/pvic/attn.py official repository unverified BSD-3-Clause (permissive) · b34159e5e7a7d936 · report

Tasks

Human-Object Interaction DetectionObject

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Human-Object Interaction Detection HICO-DET PViC-SwinL mAP 44.32 #3 of 55 Archive leaderboard report
Human-Object Interaction Detection HICO-DET PViC-R50 mAP 34.69 #15 of 55 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEConvolutionDense ConnectionsDetrDropoutFeedforward NetworkLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections