Related papers: Decoupled Prompt-Adapter Tuning for Continual Acti…

Current methods for dense 3D point tracking in dynamic scenes typically rely on pairwise processing, require known camera poses, or assume temporal ordering of input frames, thereby constraining their flexibility and applicability.…

Domain-adaptive continual pretraining (DAPT) is a state-of-the-art technique that further trains a language model (LM) on its pretraining task, e.g., masked language modeling (MLM), when common domain adaptation via LM fine-tuning is not…

Personalizing diffusion models using limited data presents significant challenges, including overfitting, loss of prior knowledge, and degradation of text alignment. Overfitting leads to shifts in the noise prediction distribution,…

In recent years, imitation learning has made progress in the field of robotic manipulation. However, it still faces challenges when addressing complex long-horizon tasks with deformable objects, such as high-dimensional state spaces,…

Videos contain rich spatio-temporal information. Traditional methods for extracting motion, used in tasks such as action recognition, often rely on visual contents rather than precise motion features. This phenomenon is referred to as…

Prompt tuning, a parameter- and data-efficient transfer learning paradigm that tunes only a small number of parameters in a model's input space, has become a trend in the vision community since the emergence of large vision-language models…

The Segment Anything Model (SAM) has exhibited outstanding performance in various image segmentation tasks. Despite being trained with over a billion masks, SAM faces challenges in mask prediction quality in numerous scenarios, especially…

We present a novel framework, Action Progression Network (APN), for temporal action detection (TAD) in videos. The framework locates actions in videos by detecting the action evolution process. To encode the action evolution, we quantify a…

Recent pre-trained vision-language models (PT-VLMs) often face a Multi-Domain Task Incremental Learning (MTIL) scenario in practice, where several classes and domains of multi-modal tasks are incrementally arrived. Without access to…

We propose Consistency-guided Prompt learning (CoPrompt), a new fine-tuning method for vision-language models. Our approach improves the generalization of large foundation models when fine-tuned on downstream tasks in a few-shot setting.…

With advances in data-driven machine learning research, a wide variety of prediction models have been proposed to capture spatio-temporal features for the analysis of video streams. Recognising actions and detecting action transitions…

Exploring open-vocabulary video action recognition is a promising venture, which aims to recognize previously unseen actions within any arbitrary set of categories. Existing methods typically adapt pretrained image-text models to the video…

Prompt learning is one of the most effective paradigms for adapting pre-trained vision-language models (VLMs) to the biomedical image classification tasks in few shot scenarios. However, most of the current prompt learning methods only used…

The integration of AI into modern critical infrastructure systems, such as healthcare, has introduced new vulnerabilities that can significantly impact workflow, efficiency, and safety. Additionally, the increased connectivity has made…

Distribution shift widely exists in medical images acquired from different medical centres and poses a significant obstacle to deploying the pre-trained semantic segmentation model in real-world applications. Test-time adaptation has proven…

Adapter-Tuning (AT) method involves freezing a pre-trained model and introducing trainable adapter modules to acquire downstream knowledge, thereby calibrating the model for better adaptation to downstream tasks. This paper proposes a…

Prompt-based continual learning provides a rehearsal-free solution by tuning small sets of parameters while keeping pre-trained models frozen. To meet the complex demands of sequential tasks, it is crucial to integrate task-specific…

Activity recognition is the ability to identify and recognize the action or goals of the agent. The agent can be any object or entity that performs action that has end goals. The agents can be a single agent performing the action or group…

For more efficient generalization to unseen domains (classes), most Few-shot Segmentation (FSS) would directly exploit pre-trained encoders and only fine-tune the decoder, especially in the current era of large models. However, such fixed…

The point process is a solid framework to model sequential data, such as videos, by exploring the underlying relevance. As a challenging problem for high-level video understanding, weakly supervised action recognition and localization in…