{"type":"ScholarlyArticle","title":"TEST-V: TEst-time Support-set Tuning for Zero-shot Video Classification","authors":[{"name":"Rui Yan","slug":"rui-yan","given":"Rui","family":"Yan","affiliation":""},{"name":"Jin Wang","slug":"jin-wang","given":"Jin","family":"Wang","affiliation":""},{"name":"Hongyu Qu","slug":"hongyu-qu","given":"Hongyu","family":"Qu","affiliation":""},{"name":"Xiaoyu Du","slug":"xiaoyu-du","given":"Xiaoyu","family":"Du","affiliation":""},{"name":"Dong Zhang","slug":"dong-zhang","given":"Dong","family":"Zhang","affiliation":""},{"name":"Jinhui Tang","slug":"jinhui-tang","given":"Jinhui","family":"Tang","affiliation":""},{"name":"Tieniu Tan","slug":"tieniu-tan","given":"Tieniu","family":"Tan","affiliation":""}],"abstract":"Recently, adapting Vision Language Models (VLMs) to zero-shot visual classification by tuning class embedding with a few prompts (Test-time Prompt Tuning, TPT) or replacing class names with generated visual samples (support-set) has shown promising results. However, TPT cannot avoid the semantic gap between modalities while the support-set cannot be tuned. To this end, we draw on each other's strengths and propose a novel framework, namely TEst-time Support-set Tuning for zero-shot Video Classification (TEST-V). It first dilates the support-set with multiple prompts (Multi-prompting Support-set Dilation, MSD) and then erodes the support-set via learnable weights to mine key cues dynamically (Temporal-aware Support-set Erosion, TSE). Specifically, i) MSD expands the support samples for each class based on multiple prompts inquired from LLMs to enrich the diversity of the support-set. ii) TSE tunes the support-set with factorized learnable weights according to the temporal prediction consistency in a self-supervised manner to dig pivotal supporting cues for each class. TEST-V achieves state-of-the-art results across four benchmarks and shows good interpretability.","doi":"10.24963/ijcai.2025/239","url":"https://ijcai.org/proceedings/2025/239","pdf":"https://ijcai.org/proceedings/2025/0239.pdf","markdown":"https://ijcai.org/proceedings/2025/239.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/239","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Computer Vision","track":"Main Track","number":239,"pages":{"first":2143,"last":2151},"keywords":["Computer Vision: CV: Video analysis and understanding","Computer Vision: CV: Vision, language and reasoning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}