相关论文: Knowledge Prompting for Few-shot Action Recognitio…

Human educators possess an intrinsic ability to anticipate and seek educational explanations from students, which drives them to pose thought-provoking questions when students cannot articulate these explanations independently. We aim to…

Vision-language foundation models pretrained on large-scale data provide a powerful tool for many visual understanding tasks. Notably, many vision-language models build two encoders (visual and textual) that can map two modalities into the…

Pre-trained vision-language models, e.g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning. Recently, learnable prompts achieve state-of-the-art performance, which however are prone to…

We present a generative framework for zero-shot action recognition where some of the possible action classes do not occur in the training data. Our approach is based on modeling each action class using a probability distribution whose…

Recognizing a particular command or a keyword, keyword spotting has been widely used in many voice interfaces such as Amazon's Alexa and Google Home. In order to recognize a set of keywords, most of the recent deep learning based approaches…

The Contrastive Language-Image Pre-training (CLIP) has recently shown remarkable generalization on "zero-shot" training and has applied to many downstream tasks. We explore the adaptation of CLIP to achieve a more efficient and generalized…

Current few-shot action recognition involves two primary sources of information for classification:(1) intra-video information, determined by frame content within a single video clip, and (2) inter-video information, measured by…

The effectiveness of prompt learning has been demonstrated in different pre-trained language models. By formulating suitable template and choosing representative label mapping, prompt learning can be used as an efficient knowledge probe.…

This study presents a comprehensive, long-term project to explore the effectiveness of various prompting techniques in detecting dialogical mental manipulation. We implement Chain-of-Thought prompting with Zero-Shot and Few-Shot settings on…

We present a novel method for few-shot video classification, which performs appearance and temporal alignments. In particular, given a pair of query and support videos, we conduct appearance alignment via frame-level feature matching to…

The emergence of attention-based transformer models has led to their extensive use in various tasks, due to their superior generalization and transfer properties. Recent research has demonstrated that such models, when prompted…

Few-shot learning aims to train models that can be generalized to novel classes with only a few samples. Recently, a line of works are proposed to enhance few-shot learning with accessible semantic information from class names. However,…

Few-shot learning has been successfully applied to medical image classification as only very few medical examples are available for training. Due to the challenging problem of limited number of annotated medical images, image…

Prompt learning is a new learning paradigm which reformulates downstream tasks as similar pretraining tasks on pretrained models by leveraging textual prompts. Recent works have demonstrated that prompt learning is particularly useful for…

Vision-language models (VLMs) classify the query video by calculating a similarity score between the visual features and text-based class label representations. Recently, large language models (LLMs) have been used to enrich the text-based…

Text classification tends to struggle when data is deficient or when it needs to adapt to unseen classes. In such challenging scenarios, recent studies have used meta-learning to simulate the few-shot task, in which new queries are compared…

Prompt-based knowledge probing for 1-hop relations has been used to measure how much world knowledge is stored in pretrained language models. Existing work uses considerable amounts of data to tune the prompts for better performance. In…

Recent advances on prompt-tuning cast few-shot classification tasks as a masked language modeling problem. By wrapping input into a template and using a verbalizer which constructs a mapping between label space and label word space,…

Zero-shot action recognition, which recognizes actions in videos without having received any training examples, is gaining wide attention considering it can save labor costs and training time. Nevertheless, the performance of zero-shot…

The human visual system has the remarkably ability to be able to effortlessly learn novel concepts from only a few examples. Mimicking the same behavior on machine learning vision systems is an interesting and very challenging research…