Related papers: VLOD-TTA: Test-Time Adaptation of Vision-Language …

Existing temporal action detection (TAD) methods rely on large training data including segment-level annotations, limited to recognizing previously seen classes alone during inference. Collecting and annotating a large training set for each…

Generative Zero-shot learning (ZSL) learns a generator to synthesize visual samples for unseen classes, which is an effective way to advance ZSL. However, existing generative methods rely on the conditions of Gaussian noise and the…

Test-time adaptation (TTA) enhances the zero-shot robustness under distribution shifts by leveraging unlabeled test data during inference. Despite notable advances, several challenges still limit its broader applicability. First, most…

Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. While standard TAD follows fully supervised learning with closed-set setting on large training data, recent zero-shot…

Test-time adaptation (TTA) is a technique aimed at enhancing the generalization performance of models by leveraging unlabeled samples solely during prediction. Given the need for robustness in neural network systems when faced with…

This paper introduces Unified Language-driven Zero-shot Domain Adaptation (ULDA), a novel task setting that enables a single model to adapt to diverse target domains without explicit domain-ID knowledge. We identify the constraints in the…

Achieving truly adaptive embodied intelligence requires agents that learn not just by imitating static demonstrations, but by continuously improving through environmental interaction, which is akin to how humans master skills through…

Transductive zero-shot learning with vision-language models leverages image-image similarities within the dataset to achieve better classification accuracy compared to the inductive setting. However, there is little work that explores the…

Vision-Language-Action (VLA) models are advancing autonomous driving by replacing modular pipelines with unified end-to-end architectures. However, current VLAs face two expensive requirements: (1) massive dataset collection, and (2) dense…

Zero-shot referring expression comprehension aims at localizing bounding boxes in an image corresponding to provided textual prompts, which requires: (i) a fine-grained disentanglement of complex visual scene and textual context, and (ii) a…

Vision Transformer (ViT) is becoming more popular in image processing. Specifically, we investigate the effectiveness of test-time adaptation (TTA) on ViT, a technique that has emerged to correct its prediction during test-time by itself.…

Test-time adaptation is a promising research direction that allows the source model to adapt itself to changes in data distribution without any supervision. Yet, current methods are usually evaluated on benchmarks that are only a…

Multimodal Large Language Models (MLLMs) have shown strong performance on Video Temporal Grounding (VTG). However, their coarse recognition capabilities are insufficient for fine-grained temporal understanding, making task-specific…

Deep learning models are transforming agricultural applications by enabling automated phenotyping, monitoring, and yield estimation. However, their effectiveness heavily depends on large amounts of annotated training data, which can be…

Open-vocabulary object detection with vision-language models (VLMs) such as Grounding DINO suffers from performance degradation under test-time distribution shifts, primarily due to semantic misalignment between text embeddings and shifted…

The era of vision-language models (VLMs) trained on web-scale datasets challenges conventional formulations of "open-world" perception. In this work, we revisit the task of few-shot object detection (FSOD) in the context of recent…

Video Anomaly Detection (VAD) has traditionally been framed as binary classification or outlier detection, providing neither interpretable reasoning nor precise spatial localization of anomalous events. While Vision-Language Models (VLMs)…

Test-time adaptation paradigm provides flexibility towards domain shifts by performing immediate adaptation on unlabeled target data from the source model. Vision-Language Models (VLMs) leverage their generalization capabilities for diverse…

Pre-trained vision-language models, such as CLIP, show impressive zero-shot recognition ability and can be easily transferred to specific downstream tasks via prompt tuning, even with limited training data. However, existing prompt tuning…

Deep neural networks often encounter significant performance drops while facing with domain shifts between training (source) and test (target) data. To address this issue, Test Time Adaptation (TTA) methods have been proposed to adapt…