{"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/enhancing-zero-shot-facial-expression","title":"Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer","arxiv_id":"2405.19100","date":"2024-05-29","proceeding":null,"authors":["Zengqun Zhao","Yu Cao","Shaogang Gong","Ioannis Patras"],"abstract":"Current facial expression recognition (FER) models are often designed in a supervised learning manner and thus are constrained by the lack of large-scale facial expression images with high-quality annotations. Consequently, these models often fail to generalize well, performing poorly on unseen images in inference. Vision-language-based zero-shot models demonstrate a promising potential for addressing such challenges. However, these models lack task-specific knowledge and therefore are not optimized for the nuances of recognizing facial expressions. To bridge this gap, this work proposes a novel method, Exp-CLIP, to enhance zero-shot FER by transferring the task knowledge from large language models (LLMs). Specifically, based on the pre-trained vision-language encoders, we incorporate a projection head designed to map the initial joint vision-language space into a space that captures representations of facial actions. To train this projection head for subsequent zero-shot predictions, we propose to align the projected visual representations with task-specific semantic meanings derived from the LLM encoder, and the text instruction-based strategy is employed to customize the LLM knowledge. Given unlabelled facial data and efficient training of the projection head, Exp-CLIP achieves superior zero-shot results to the CLIP models and several other large vision-language models (LVLMs) on seven in-the-wild FER datasets. The code and pre-trained models are available at https://github.com/zengqunzhao/Exp-CLIP.","url_abs":"https://arxiv.org/abs/2405.19100v3","url_pdf":"https://arxiv.org/pdf/2405.19100v3.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":"enhancing-zero-shot-facial-expression","repo_url":"https://github.com/zengqunzhao/exp-clip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"facial-expression-recognition-1","task_name":"Facial Expression Recognition"},{"task_slug":"facial-expression-recognition","task_name":"Facial Expression Recognition (FER)"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"zero-shot-facial-expression-recognition","task_name":"Zero-Shot Facial Expression Recognition"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.19100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19100"}},"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/zengqunzhao/exp-clip","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":7},"by_repo_kind":{"official":{"samples":10,"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":"98f385d847636a3e","entry":"basic_clean","repo":"zengqunzhao/exp-clip","repo_kind":"official","path":"models/clip/simple_tokenizer.py","file_url":"https://github.com/zengqunzhao/exp-clip/blob/HEAD/models/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"zengqunzhao/exp-clip","repo_kind":"official","path":"models/clip/simple_tokenizer.py","file_url":"https://github.com/zengqunzhao/exp-clip/blob/HEAD/models/clip/simple_tokenizer.py","link_basis":"harvester_set","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":"d919ae32e5e4e616"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"zengqunzhao/exp-clip","repo_kind":"official","path":"models/clip/simple_tokenizer.py","file_url":"https://github.com/zengqunzhao/exp-clip/blob/HEAD/models/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"9a9839a0184a9bc9","entry":"beam_search","repo":"zengqunzhao/exp-clip","repo_kind":"official","path":"models/BLIP2_T5.py","file_url":"https://github.com/zengqunzhao/exp-clip/blob/HEAD/models/BLIP2_T5.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":"9a9839a0184a9bc9"}},{"code_sha256_prefix":"39e6b23b55f376ea","entry":"build_model","repo":"zengqunzhao/exp-clip","repo_kind":"official","path":"models/clip/model.py","file_url":"https://github.com/zengqunzhao/exp-clip/blob/HEAD/models/clip/model.py","link_basis":"harvester_set","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":"39e6b23b55f376ea"}},{"code_sha256_prefix":"f239483928dcb19e","entry":"generate","repo":"zengqunzhao/exp-clip","repo_kind":"official","path":"models/BLIP2_T5.py","file_url":"https://github.com/zengqunzhao/exp-clip/blob/HEAD/models/BLIP2_T5.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":"f239483928dcb19e"}},{"code_sha256_prefix":"b90f6523b6bb8584","entry":"generate_text_only","repo":"zengqunzhao/exp-clip","repo_kind":"official","path":"models/BLIP2_T5.py","file_url":"https://github.com/zengqunzhao/exp-clip/blob/HEAD/models/BLIP2_T5.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":"b90f6523b6bb8584"}},{"code_sha256_prefix":"f6f30e41636ae569","entry":"load","repo":"zengqunzhao/exp-clip","repo_kind":"official","path":"models/clip/clip.py","file_url":"https://github.com/zengqunzhao/exp-clip/blob/HEAD/models/clip/clip.py","link_basis":"harvester_set","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":"f6f30e41636ae569"}},{"code_sha256_prefix":"1365e3d0cde142cd","entry":"test_data_loader","repo":"zengqunzhao/exp-clip","repo_kind":"official","path":"data_loader/video_dataloader.py","file_url":"https://github.com/zengqunzhao/exp-clip/blob/HEAD/data_loader/video_dataloader.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":"1365e3d0cde142cd"}},{"code_sha256_prefix":"0b41c7a3b52f769f","entry":"train_data_loader","repo":"zengqunzhao/exp-clip","repo_kind":"official","path":"data_loader/video_dataloader.py","file_url":"https://github.com/zengqunzhao/exp-clip/blob/HEAD/data_loader/video_dataloader.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":"0b41c7a3b52f769f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}