{"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/shine-saliency-aware-hierarchical-negative","title":"SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding","arxiv_id":"2407.05118","date":"2024-07-06","proceeding":null,"authors":["Zixu Cheng","Yujiang Pu","Shaogang Gong","Parisa Kordjamshidi","Yu Kong"],"abstract":"Temporal grounding, also known as video moment retrieval, aims at locating video segments corresponding to a given query sentence. The compositional nature of natural language enables the localization beyond predefined events, posing a certain challenge to the compositional generalizability of existing methods. Recent studies establish the correspondence between videos and queries through a decompose-reconstruct manner to achieve compositional generalization. However, they only consider dominant primitives and build negative queries through random sampling and recombination, resulting in semantically implausible negatives that hinder the models from learning rational compositions. In addition, recent DETR-based methods still underperform in compositional temporal grounding, showing irrational saliency responses when given negative queries that have subtle differences from positive queries. To address these limitations, we first propose a large language model-driven method for negative query construction, utilizing GPT-3.5-Turbo to generate semantically plausible hard negative queries. Subsequently, we introduce a coarse-to-fine saliency ranking strategy, which encourages the model to learn the multi-granularity semantic relationships between videos and hierarchical negative queries to boost compositional generalization. Extensive experiments on two challenging benchmarks validate the effectiveness and generalizability of our proposed method. Our code is available at https://github.com/zxccade/SHINE.","url_abs":"https://arxiv.org/abs/2407.05118v2","url_pdf":"https://arxiv.org/pdf/2407.05118v2.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":"shine-saliency-aware-hierarchical-negative","repo_url":"https://github.com/zxccade/shine","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"moment-retrieval","task_name":"Moment Retrieval"},{"task_slug":"saliency-ranking","task_name":"Saliency Ranking"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.05118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05118"}},"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/zxccade/SHINE","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":6,"ran_draft_wrong":1,"ran_honours":1,"ran_violates":1,"unverified":4},"by_repo_kind":{"official":{"samples":13,"ran":9,"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":13,"samples":[{"code_sha256_prefix":"d6ca656c20df137a","entry":"build_position_encoding","repo":"zxccade/SHINE","repo_kind":"official","path":"shine/position_encoding.py","file_url":"https://github.com/zxccade/SHINE/blob/HEAD/shine/position_encoding.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d6ca656c20df137a"}},{"code_sha256_prefix":"e62dd692b8390088","entry":"coarse_ranking","repo":"zxccade/SHINE","repo_kind":"official","path":"shine/ctf_ranking.py","file_url":"https://github.com/zxccade/SHINE/blob/HEAD/shine/ctf_ranking.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e62dd692b8390088"}},{"code_sha256_prefix":"2fb84c87e0a7ca0e","entry":"div_loss","repo":"zxccade/SHINE","repo_kind":"official","path":"shine/ctf_ranking.py","file_url":"https://github.com/zxccade/SHINE/blob/HEAD/shine/ctf_ranking.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"2fb84c87e0a7ca0e"}},{"code_sha256_prefix":"6897880b6ce14c94","entry":"inverse_sigmoid","repo":"zxccade/SHINE","repo_kind":"official","path":"shine/model.py","file_url":"https://github.com/zxccade/SHINE/blob/HEAD/shine/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":"6897880b6ce14c94"}},{"code_sha256_prefix":"db2249562e0e9af0","entry":"kl_loss","repo":"zxccade/SHINE","repo_kind":"official","path":"shine/ctf_ranking.py","file_url":"https://github.com/zxccade/SHINE/blob/HEAD/shine/ctf_ranking.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"db2249562e0e9af0"}},{"code_sha256_prefix":"1c17153fb5488283","entry":"mask_logits","repo":"zxccade/SHINE","repo_kind":"official","path":"shine/text_encoder.py","file_url":"https://github.com/zxccade/SHINE/blob/HEAD/shine/text_encoder.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1c17153fb5488283"}},{"code_sha256_prefix":"a959a00d132fc4ac","entry":"prepare_batch_inputs","repo":"zxccade/SHINE","repo_kind":"official","path":"shine/start_end_dataset.py","file_url":"https://github.com/zxccade/SHINE/blob/HEAD/shine/start_end_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a959a00d132fc4ac"}},{"code_sha256_prefix":"690e7cb41525c697","entry":"prepare_batch_inputs_train","repo":"zxccade/SHINE","repo_kind":"official","path":"shine/start_end_dataset.py","file_url":"https://github.com/zxccade/SHINE/blob/HEAD/shine/start_end_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"690e7cb41525c697"}},{"code_sha256_prefix":"b7639c2e8b83837b","entry":"span_cxw_to_xx","repo":"zxccade/SHINE","repo_kind":"official","path":"shine/span_utils.py","file_url":"https://github.com/zxccade/SHINE/blob/HEAD/shine/span_utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b7639c2e8b83837b"}},{"code_sha256_prefix":"081c8abd57d082fd","entry":"accuracy","repo":"zxccade/SHINE","repo_kind":"official","path":"shine/misc.py","file_url":"https://github.com/zxccade/SHINE/blob/HEAD/shine/misc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"081c8abd57d082fd"}},{"code_sha256_prefix":"a82091666b9db8cf","entry":"multi_head_attention_forward","repo":"zxccade/SHINE","repo_kind":"official","path":"shine/attention.py","file_url":"https://github.com/zxccade/SHINE/blob/HEAD/shine/attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"code_sha256_prefix":"7114f025044af9b4","entry":"span_xx_to_cxw","repo":"zxccade/SHINE","repo_kind":"official","path":"shine/span_utils.py","file_url":"https://github.com/zxccade/SHINE/blob/HEAD/shine/span_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7114f025044af9b4"}},{"code_sha256_prefix":"e4ae5582a2533cdb","entry":"temporal_iou","repo":"zxccade/SHINE","repo_kind":"official","path":"shine/span_utils.py","file_url":"https://github.com/zxccade/SHINE/blob/HEAD/shine/span_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e4ae5582a2533cdb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}