Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings, 2026</p>\n","updatedAt":"2026-05-18T15:36:03.202Z","author":{"_id":"67531f32b598bcf2cc4ea40f","avatarUrl":"/avatars/7e1609b6ff565cd08e812ee91d83fdbb.svg","fullname":"Yuyuan liu","name":"yyliu01","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6359549760818481},"editors":["yyliu01"],"editorAvatarUrls":["/avatars/7e1609b6ff565cd08e812ee91d83fdbb.svg"],"reactions":[],"isReport":false}},{"id":"6a0bc0c87f332b13403e0ed3","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":357,"isUserFollowing":false},"createdAt":"2026-05-19T01:45:44.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [PRIMED: Adaptive Modality Suppression for Referring Audio-Visual Segmentation via Biased Competition](https://huggingface.co/papers/2605.07154) (2026)\n* [SOUPLE: Enhancing Audio-Visual Localization and Segmentation with Learnable Prompt Contexts](https://huggingface.co/papers/2603.22732) (2026)\n* [LightAVSeg: Lightweight Audio-Visual Segmentation](https://huggingface.co/papers/2605.08805) (2026)\n* [TB-AVA: Text as a Semantic Bridge for Audio-Visual Parameter Efficient Finetuning](https://huggingface.co/papers/2605.11572) (2026)\n* [Leave No Stone Unturned: Uncovering Holistic Audio-Visual Intrinsic Coherence for Deepfake Detection](https://huggingface.co/papers/2603.23960) (2026)\n* [Look, Listen and Segment: Towards Weakly Supervised Audio-Visual Semantic Segmentation](https://huggingface.co/papers/2603.21948) (2026)\n* [X2SAM: Any Segmentation in Images and Videos](https://huggingface.co/papers/2605.00891) (2026)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"<p>This is an automated message from the <a href=\"https://huggingface.co/librarian-bots\">Librarian Bot</a>. I found the following papers similar to this paper. </p>\n<p>The following papers were recommended by the Semantic Scholar API </p>\n<ul>\n<li><a href=\"https://huggingface.co/papers/2605.07154\">PRIMED: Adaptive Modality Suppression for Referring Audio-Visual Segmentation via Biased Competition</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2603.22732\">SOUPLE: Enhancing Audio-Visual Localization and Segmentation with Learnable Prompt Contexts</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.08805\">LightAVSeg: Lightweight Audio-Visual Segmentation</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.11572\">TB-AVA: Text as a Semantic Bridge for Audio-Visual Parameter Efficient Finetuning</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2603.23960\">Leave No Stone Unturned: Uncovering Holistic Audio-Visual Intrinsic Coherence for Deepfake Detection</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2603.21948\">Look, Listen and Segment: Towards Weakly Supervised Audio-Visual Semantic Segmentation</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.00891\">X2SAM: Any Segmentation in Images and Videos</a> (2026)</li>\n</ul>\n<p> Please give a thumbs up to this comment if you found it helpful!</p>\n<p> If you want recommendations for any Paper on Hugging Face checkout <a href=\"https://huggingface.co/spaces/librarian-bots/recommend_similar_papers\">this</a> Space</p>\n<p> You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: <code><span class=\"SVELTE_PARTIAL_HYDRATER contents\" data-target=\"UserMention\" data-props=\"{&quot;user&quot;:&quot;librarian-bot&quot;}\"><span class=\"inline-block\"><span class=\"contents\"><a href=\"/librarian-bot\">@<span class=\"underline\">librarian-bot</span></a></span> </span></span> recommend</code></p>\n","updatedAt":"2026-05-19T01:45:44.055Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":357,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7078337669372559},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2506.01015","authors":[{"_id":"6a0795ef75184a0d71e0213a","user":{"_id":"67531f32b598bcf2cc4ea40f","avatarUrl":"/avatars/7e1609b6ff565cd08e812ee91d83fdbb.svg","isPro":false,"fullname":"Yuyuan liu","user":"yyliu01","type":"user","name":"yyliu01"},"name":"Yuyuan Liu","status":"claimed_verified","statusLastChangedAt":"2026-05-18T09:41:45.894Z","hidden":false},{"_id":"6a0795ef75184a0d71e0213b","name":"Yuanhong Chen","hidden":false},{"_id":"6a0795ef75184a0d71e0213c","name":"Chong Wang","hidden":false},{"_id":"6a0795ef75184a0d71e0213d","name":"Junlin Han","hidden":false},{"_id":"6a0795ef75184a0d71e0213e","name":"Junde Wu","hidden":false},{"_id":"6a0795ef75184a0d71e0213f","name":"Can Peng","hidden":false},{"_id":"6a0795ef75184a0d71e02140","name":"Jingkun Chen","hidden":false},{"_id":"6a0795ef75184a0d71e02141","name":"Yu Tian","hidden":false},{"_id":"6a0795ef75184a0d71e02142","name":"Gustavo Carneiro","hidden":false}],"publishedAt":"2026-05-14T00:00:00.000Z","submittedOnDailyAt":"2026-05-18T00:00:00.000Z","title":"AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting","submittedOnDailyBy":{"_id":"67531f32b598bcf2cc4ea40f","avatarUrl":"/avatars/7e1609b6ff565cd08e812ee91d83fdbb.svg","isPro":false,"fullname":"Yuyuan liu","user":"yyliu01","type":"user","name":"yyliu01"},"summary":"Segment Anything Model 2 (SAM2) exhibits strong generalisation for promptable segmentation in video clips; however, its integration with the audio modality remains underexplored. Existing approaches either convert audio into visual prompts (e.g., boxes) via foundation models, or inject adapters into the image encoder for audio-visual fusion. Yet both directions fall short in human-in-the-loop scenarios due to limited prompt accuracy and increased inference overhead. In particular, these adapter-based methods often suffer from audio prompt dilution, where the signal gradually weakens as it propagates through the network. In this work, we propose AuralSAM2, which integrates audio into SAM2 while largely preserving its promptable segmentation capability. Its core module, AuralFuser, fuses audio and visual features to generate sparse and dense prompts. Guided by audio and built upon SAM2's feature pyramid, these prompts propagate auditory cues across visual layers, reinforcing cross-modal influence. To further align modalities, we introduce an audio-guided contrastive loss that emphasises auditory relevance in dominant visual features. Our method achieves notable accuracy gains on public benchmarks with only minimal impact on the interactive efficiency of promptable segmentation. Our code is available at https://github.com/yyliu01/AuralSAM2.","upvotes":0,"discussionId":"6a0795ef75184a0d71e02143","githubRepo":"https://github.com/yyliu01/AuralSAM2","githubRepoAddedBy":"user","ai_summary":"AuralSAM2 integrates audio into SAM2 through an AuralFuser module that generates sparse and dense prompts, enhancing cross-modal influence while maintaining interactive segmentation efficiency.","ai_keywords":["Segment Anything Model 2","audio-visual fusion","promptable segmentation","AuralFuser","audio-guided contrastive loss","feature pyramid","cross-modal influence"],"githubStars":9,"organization":{"_id":"627bbc28fbab61b048eba8b6","name":"Oxford","fullname":"University of Oxford","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/68e396f2b5bb631e9b2fac9a/u0ey2LfYu6uG6iu8m_kH7.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[],"acceptLanguages":["en"],"organization":{"_id":"627bbc28fbab61b048eba8b6","name":"Oxford","fullname":"University of Oxford","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/68e396f2b5bb631e9b2fac9a/u0ey2LfYu6uG6iu8m_kH7.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2506/2506.01015.md"}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2506.01015 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2506.01015 in a Space README.md to link it from this page.

Add this paper to a collection to link it from this page.