相关论文: CPL-NoViD: Context-Aware Prompt-based Learning for…

In-context imitation learning enables robots to adapt to new tasks from a small number of demonstrations without additional training. However, existing approaches typically condition only on state-action trajectories and lack explicit…

The success of Vision Language Models (VLMs) on various vision-language tasks heavily relies on pre-training with large scale web-crawled datasets. However, the noisy and incomplete nature of web data makes dataset scale crucial for…

Predictive learning ideally builds the world model of physical processes in one or more given environments. Typical setups assume that we can collect data from all environments at all times. In practice, however, different prediction tasks…

Video anomaly detection under weak supervision presents significant challenges, particularly due to the lack of frame-level annotations during training. While prior research has utilized graph convolution networks and self-attention…

Increasing the semantic understanding and contextual awareness of machine learning models is important for improving robustness and reducing susceptibility to data shifts. In this work, we leverage contextual awareness for the anomaly…

Prompt learning as a parameter-efficient method that has been widely adopted to adapt Vision-Language Models (VLMs) to downstream tasks. While hard-prompt design requires domain expertise and iterative optimization, soft-prompt methods rely…

Fine-tuned pre-trained language models (PLMs) have achieved awesome performance on almost all NLP tasks. By using additional prompts to fine-tune PLMs, we can further stimulate the rich knowledge distributed in PLMs to better serve…

Large language models (LLMs) have triggered a new stream of research focusing on compressing the context length to reduce the computational cost while ensuring the retention of helpful information for LLMs to answer the given question.…

This technical report presents our first place winning solution for temporal action detection task in CVPR-2022 AcitivityNet Challenge. The task aims to localize temporal boundaries of action instances with specific classes in long…

Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to…

Detection of anomalous events in videos is an important problem in applications such as surveillance. Video anomaly detection (VAD) is well-studied in the one-class classification (OCC) and weakly supervised (WS) settings. However, fully…

Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the…

Real-world applications of contextual bandits often exhibit non-stationarity due to seasonality, serendipity, and evolving social trends. While a number of non-stationary contextual bandit learning algorithms have been proposed in the…

The performance of Visio-Language Transformers drops sharply when an input modality (e.g., image) is missing, because the model is forced to make predictions using incomplete information. Existing missing-aware prompt methods help reduce…

Language identification (LID) recognizes the language of a spoken utterance automatically. According to recent studies, LID models trained with an automatic speech recognition (ASR) task perform better than those trained with a LID task…

The performance of machine learning model can be further improved if contextual cues are provided as input along with base features that are directly related to an inference task. In offline learning, one can inspect historical training…

Contrastive Language-Image Pretraining (CLIP) model has exhibited remarkable efficacy in establishing cross-modal connections between texts and images, yielding impressive performance across a broad spectrum of downstream applications…

Automated log analysis is crucial in modern software-intensive systems for facilitating program comprehension throughout software maintenance and engineering life cycles. Existing methods perform tasks such as log parsing and log anomaly…

We propose Context-Adaptive Multi-Prompt Embedding, a novel approach to enrich semantic representations in vision-language contrastive learning. Unlike standard CLIP-style models that rely on a single text embedding, our method introduces…

When we interact with small screen devices, sometimes we make errors, due to our abilities/disabilities, contextual factors that distract our attention or problems related to the interface. Recovering from these errors may be time consuming…