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

Deep learning based methods often suffer from performance degradation caused by domain shift. In recent years, many sophisticated network structures have been designed to tackle this problem. However, the advent of large model trained on…

Recently, prompt learning has demonstrated remarkable success in adapting pre-trained Vision-Language Models (VLMs) to various downstream tasks such as image classification. However, its application to the downstream Image-Text Retrieval…

Test-time prompt tuning enhances zero-shot generalization of vision-language models but tends to ignore the relatedness among test samples during inference. Online test-time prompt tuning provides a simple way to leverage the information in…

The Base-New Trade-off (BNT) problem universally exists during the optimization of CLIP-based prompt tuning, where continuous fine-tuning on base (target) classes leads to a simultaneous decrease of generalization ability on new (unseen)…

Since autonomous driving systems usually face dynamic and ever-changing environments, continual test-time adaptation (CTTA) has been proposed as a strategy for transferring deployed models to continually changing target domains. However,…

Unsupervised domain adaption (UDA) aims to adapt models learned from a well-annotated source domain to a target domain, where only unlabeled samples are given. Current UDA approaches learn domain-invariant features by aligning source and…

Existing video-based action recognition systems typically require dense annotation and struggle in environments when there is significant distribution shift relative to the training data. Current methods for video domain adaptation…

Continuous action recognition is more challenging than isolated recognition because classification and segmentation must be simultaneously carried out. We build on the well known dynamic time warping (DTW) framework and devise a novel…

Procedure Planning in instructional videos entails generating a sequence of action steps based on visual observations of the initial and target states. Despite the rapid progress in this task, there remain several critical challenges to be…

Panoramic Activity Recognition (PAR) aims to identify multi-granularity behaviors performed by multiple persons in panoramic scenes, including individual activities, group activities, and global activities. Previous methods 1) heavily rely…

Reliable anticipation of pedestrian trajectory is imperative for the operation of autonomous vehicles and can significantly enhance the functionality of advanced driver assistance systems. While significant progress has been made in the…

Surgical phase recognition has become a crucial requirement in laparoscopic surgery, enabling various clinical applications like surgical risk forecasting. Current methods typically identify the surgical phase using individual frame-wise…

Text-based person retrieval (TPR) has gained significant attention as a fine-grained and challenging task that closely aligns with practical applications. Tailoring CLIP to person domain is now a emerging research topic due to the abundant…

For CLIP-based prompt tuning, introducing more data as additional knowledge for enhancing fine-tuning process is proved to be an effective approach. Existing data amplification strategies for prompt tuning typically rely on external…

Clinical AI systems frequently suffer performance decay post-deployment due to temporal data shifts, such as evolving populations, diagnostic coding updates (e.g., ICD-9 to ICD-10), and systemic shocks like the COVID-19 pandemic. Addressing…

Prompt tuning is a parameter-efficient way to deploy large-scale pre-trained models to downstream tasks by adding task-specific tokens. In terms of vision-language pre-trained (VLP) models, prompt tuning often requires a large number of…

Deep neural networks based purely on attention have been successful across several domains, relying on minimal architectural priors from the designer. In Human Action Recognition (HAR), attention mechanisms have been primarily adopted on…

Visual Prompt Tuning (VPT) of pre-trained Vision Transformers (ViTs) has proven highly effective as a parameter-efficient fine-tuning technique for adapting large models to downstream tasks with limited data. Its parameter efficiency makes…

Active Test-Time Adaptation (ATTA) improves model robustness under domain shift by selectively querying human annotations at deployment, but existing methods use heuristic uncertainty measures and suffer from low data selection efficiency,…

Large-scale vision-language models (VLMs), e.g., CLIP, learn broad visual concepts from tedious training data, showing superb generalization ability. Amount of prompt learning methods have been proposed to efficiently adapt the VLMs to…