{"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/egonce-do-egocentric-video-language-models","title":"EgoNCE++: Do Egocentric Video-Language Models Really Understand Hand-Object Interactions?","arxiv_id":"2405.17719","date":"2024-05-28","proceeding":null,"authors":["Boshen Xu","Ziheng Wang","Yang Du","Zhinan Song","Sipeng Zheng","Qin Jin"],"abstract":"Egocentric video-language pretraining is a crucial paradigm to advance the learning of egocentric hand-object interactions (EgoHOI). Despite the great success on existing testbeds, these benchmarks focus more on closed-set visual concepts or limited scenarios. Due to the occurrence of diverse EgoHOIs in the real world, we propose an open-vocabulary benchmark named EgoHOIBench to reveal the diminished performance of current egocentric video-language models (EgoVLM) on fined-grained concepts, indicating that these models still lack a full spectrum of egocentric understanding. We attribute this performance gap to insufficient fine-grained supervision and strong bias towards understanding objects rather than temporal dynamics in current methods. To tackle these issues, we introduce a novel asymmetric contrastive objective for EgoHOI named EgoNCE++. For video-to-text loss, we enhance text supervision through the generation of negative captions by leveraging the in-context learning of large language models to perform HOI-related word substitution. For text-to-video loss, we propose an object-centric positive video sampling strategy that aggregates video representations by the same nouns. Our extensive experiments demonstrate that EgoNCE++ significantly boosts open-vocabulary HOI recognition, multi-instance retrieval, and action recognition tasks across various egocentric models, with improvements of up to +26.55%. Our code is available at https://github.com/xuboshen/EgoNCEpp.","url_abs":"https://arxiv.org/abs/2405.17719v2","url_pdf":"https://arxiv.org/pdf/2405.17719v2.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":"egonce-do-egocentric-video-language-models","repo_url":"https://github.com/xuboshen/egoncepp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"multi-instance-retrieval","task_name":"Multi-Instance Retrieval"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.17719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17719"}},"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/xuboshen/EgoNCEpp","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xuboshen/egoncepp","reach":{"status":"ok"}}],"summary":{"ran":3,"ran_fixture":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"5faa817f5993f58d","entry":"EgoNCE","repo":"xuboshen/egoncepp","repo_kind":"official","path":"EgoVLPv2/model/loss.py","file_url":"https://github.com/xuboshen/egoncepp/blob/HEAD/EgoVLPv2/model/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5faa817f5993f58d"}},{"code_sha256_prefix":"544c604bc4f58d28","entry":"attn","repo":"xuboshen/EgoNCEpp","repo_kind":"official","path":"EgoVLP/model/video_transformer.py","file_url":"https://github.com/xuboshen/EgoNCEpp/blob/HEAD/EgoVLP/model/video_transformer.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"544c604bc4f58d28"}},{"code_sha256_prefix":"cc75922a52aa2e45","entry":"cols2metrics","repo":"xuboshen/EgoNCEpp","repo_kind":"official","path":"EgoVLP/model/metric.py","file_url":"https://github.com/xuboshen/EgoNCEpp/blob/HEAD/EgoVLP/model/metric.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cc75922a52aa2e45"}},{"code_sha256_prefix":"185c7b880ca6135e","entry":"sim_matrix","repo":"xuboshen/EgoNCEpp","repo_kind":"official","path":"EgoVLP/model/model.py","file_url":"https://github.com/xuboshen/EgoNCEpp/blob/HEAD/EgoVLP/model/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"185c7b880ca6135e"}},{"code_sha256_prefix":"52a134b570ef6e0c","entry":"v2t_metrics","repo":"xuboshen/EgoNCEpp","repo_kind":"official","path":"EgoVLP/model/metric.py","file_url":"https://github.com/xuboshen/EgoNCEpp/blob/HEAD/EgoVLP/model/metric.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"52a134b570ef6e0c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}