Related papers: STAR: Semantic-Temporal Adaptive Representation Le…

Few-shot segmentation (FSS) aims to segment new classes using few annotated images. While recent FSS methods have shown considerable improvements by leveraging Segment Anything Model (SAM), they face two critical limitations: insufficient…

Multi-modality image fusion, particularly infrared and visible, plays a crucial role in integrating diverse modalities to enhance scene understanding. Although early research prioritized visual quality, preserving fine details and adapting…

This paper investigates a valuable setting called few-shot unsupervised domain adaptation (FS-UDA), which has not been sufficiently studied in the literature. In this setting, the source domain data are labelled, but with few-shot per…

Few-shot learning (FSL) aims to learn novel tasks with very few labeled samples by leveraging experience from \emph{related} training tasks. In this paper, we try to understand FSL by delving into two key questions: (1) How to quantify the…

Vision Transformers (ViTs) have shown significant promise in computer vision applications. However, their performance in few-shot learning is limited by challenges in refining token-level interactions, struggling with limited training data,…

Test-time adaptation (TTA) adapts the pre-trained models during inference using unlabeled test data and has received a lot of research attention due to its potential practical value. Unfortunately, without any label supervision, existing…

Recent State Space Models (SSM), especially Mamba, have demonstrated impressive performance in visual modeling and possess superior model efficiency. However, the application of Mamba to visual tasks suffers inferior performance due to…

Few-shot anomaly detection (FSAD) methods identify anomalous regions with few known normal samples. Most existing methods rely on the generalization ability of pre-trained vision-language models (VLMs) to recognize potentially anomalous…

Point-supervised Temporal Action Localization (PTAL) adopts a lightly frame-annotated paradigm (\textit{i.e.}, labeling only a single frame per action instance) to train a model to effectively locate action instances within untrimmed…

Autonomous robotic systems should reason about resource control and its impact on subsequent maneuvers, especially when operating with limited energy budgets or restricted sensing. Learning-based control is effective in handling complex…

Despite achieving state-of-the-art zero-shot performance, existing vision-language models still fall short of few-shot transfer ability on domain-specific problems. Classical fine-tuning often fails to prevent highly expressive models from…

We present a cross-modal Transformer-based framework, which jointly encodes video data and text labels for zero-shot action recognition (ZSAR). Our model employs a conceptually new pipeline by which visual representations are learned in…

Transferring vision-language knowledge from pretrained multimodal foundation models to various downstream tasks is a promising direction. However, most current few-shot action recognition methods are still limited to a single visual…

Temporal reasoning is a critical challenge in video-language understanding, as it requires models to align semantic concepts consistently across time. While existing large vision-language models (LVLMs) and large language models (LLMs)…

Few-shot learning is often motivated by the ability of humans to learn new tasks from few examples. However, standard few-shot classification benchmarks assume that the representation is learned on a limited amount of base class data,…

Fine-grained emotion recognition (FER) plays a vital role in various fields, such as disease diagnosis, personalized recommendations, and multimedia mining. However, existing FER methods face three key challenges in real-world applications:…

Wearable human activity recognition (WHAR) models often suffer from performance degradation under real-world cross-user distribution shifts. Test-time adaptation (TTA) mitigates this degradation by adapting models online using unlabeled…

Vision-language segmentation models have recently achieved strong performance by leveraging high-level semantic object categories expressed in natural language. However, this semantic dependence limits their ability to reason about…

This paper tackles a novel yet challenging problem: how to transfer knowledge from the emerging Segment Anything Model (SAM) -- which reveals impressive zero-shot instance segmentation capacity -- to learn a compact panoramic semantic…

Over the last couple of years few-shot learning (FSL) has attracted great attention towards minimizing the dependency on labeled training examples. An inherent difficulty in FSL is the handling of ambiguities resulting from having too few…