{"list":"other","total":54,"rows":[{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"2204.04799","title":"DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning","created":"2022-04-10","cited_by_count":642},{"id":"2211.13218","title":"CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning","created":"2022-11-23","cited_by_count":450},{"id":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267},{"id":"2207.12819","title":"S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning","created":"2022-07-26","cited_by_count":246},{"id":"2302.03648","title":"Class-Incremental Learning: A Survey","created":"2023-02-07","cited_by_count":209},{"id":"2302.03241","title":"Continual Pre-training of Language Models","created":"2023-02-07","cited_by_count":198},{"id":"2303.05118","title":"SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model","created":"2023-03-09","cited_by_count":180},{"id":"2202.00874","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","created":"2022-02-02","cited_by_count":176},{"id":"2401.16386","title":"Continual Learning with Pre-Trained Models: A Survey","created":"2024-01-29","cited_by_count":154},{"id":"2112.04215","title":"Self-Supervised Models are Continual Learners","created":"2021-12-08","cited_by_count":149},{"id":"2407.15795","title":"AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection","created":"2024-07-22","cited_by_count":127},{"id":"2201.00766","title":"Class-Incremental Continual Learning into the eXtended DER-verse","created":"2022-01-03","cited_by_count":124},{"id":"2303.01904","title":"EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization","created":"2023-03-03","cited_by_count":123},{"id":"2310.07234","title":"Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality","created":"2023-10-11","cited_by_count":121},{"id":"2204.00895","title":"Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation","created":"2022-04-02","cited_by_count":113},{"id":"2303.03366","title":"Referring Multi-Object Tracking","created":"2023-03-06","cited_by_count":93},{"id":"2209.06430","title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","created":"2022-09-14","cited_by_count":74},{"id":"2307.13770","title":"E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning","created":"2023-07-25","cited_by_count":70},{"id":"2206.09059","title":"CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks","created":"2022-06-18","cited_by_count":68},{"id":"2308.15827","title":"Introducing Language Guidance in Prompt-based Continual Learning","created":"2023-08-30","cited_by_count":49},{"id":"2407.14143","title":"Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion","created":"2024-07-19","cited_by_count":47},{"id":"2212.04842","title":"PIVOT: Prompting for Video Continual Learning","created":"2022-12-09","cited_by_count":45},{"id":"2308.10445","title":"When Prompt-based Incremental Learning Does Not Meet Strong Pretraining","created":"2023-08-21","cited_by_count":41},{"id":"2111.12853","title":"Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains","created":"2021-11-25","cited_by_count":39},{"id":"2311.16494","title":"ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models","created":"2023-11-27","cited_by_count":39},{"id":"2203.14952","title":"Energy-based Latent Aligner for Incremental Learning","created":"2022-03-28","cited_by_count":37},{"id":"2308.07648","title":"Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval","created":"2023-08-15","cited_by_count":35},{"id":"2308.11073","title":"Audio-Visual Class-Incremental Learning","created":"2023-08-21","cited_by_count":33},{"id":"2104.07286","title":"Continual Learning for Fake Audio Detection","created":"2021-04-15","cited_by_count":27},{"id":"2401.10588","title":"DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval","created":"2024-01-19","cited_by_count":26},{"id":"2104.02000","title":"Can audio-visual integration strengthen robustness under multimodal attacks?","created":"2021-04-05","cited_by_count":23},{"id":"2402.04129","title":"OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning","created":"2024-02-06","cited_by_count":20},{"id":"2403.06870","title":"Semantic Residual Prompts for Continual Learning","created":"2024-03-11","cited_by_count":19},{"id":"2410.06535","title":"Happy: A Debiased Learning Framework for Continual Generalized Category Discovery","created":"2024-10-09","cited_by_count":18},{"id":"2309.08357","title":"Audio-free Prompt Tuning for Language-Audio Models","created":"2023-09-15","cited_by_count":13},{"id":"2409.18860","title":"LW2G: Learning Whether to Grow for Prompt-based Continual Learning","created":"2024-09-27","cited_by_count":9},{"id":"2312.03694","title":"Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers","created":"2023-12-06","cited_by_count":8},{"id":"2407.03813","title":"PECTP: Parameter-Efficient Cross-Task Prompts for Incremental Vision Transformer","created":"2024-07-04","cited_by_count":8},{"id":"2401.04447","title":"Class-Incremental Learning for Multi-Label Audio Classification","created":"2024-01-09","cited_by_count":6},{"id":"2302.14314","title":"Adapter Incremental Continual Learning of Efficient Audio Spectrogram Transformers","created":"2023-02-28","cited_by_count":5},{"id":"2407.12188","title":"CroMo-Mixup: Augmenting Cross-Model Representations for Continual Self-Supervised Learning","created":"2024-07-16","cited_by_count":4},{"id":"2212.10950","title":"UNIKD: UNcertainty-filtered Incremental Knowledge Distillation for Neural Implicit Representation","created":"2022-12-21","cited_by_count":3},{"id":"2401.06287","title":"Hierarchical Augmentation and Distillation for Class Incremental Audio-Visual Video Recognition","created":"2024-01-11","cited_by_count":3},{"id":"2409.00851","title":"Dissecting Temporal Understanding in Text-to-Audio Retrieval","created":"2024-09-01","cited_by_count":3},{"id":"2403.10146","title":"Multiscale Matching Driven by Cross-Modal Similarity Consistency for Audio-Text Retrieval","created":"2024-03-15","cited_by_count":2},{"id":"2409.09256","title":"Audio-text Retrieval with Transformer-based Hierarchical Alignment and Disentangled Cross-modal Representation","created":"2024-09-14","cited_by_count":2},{"id":"2409.10025","title":"DiffATR: Diffusion-based Generative Modeling for Audio-Text Retrieval","created":"2024-09-16","cited_by_count":2}],"next_cursor":null}