Related papers: RETTA: Retrieval-Enhanced Test-Time Adaptation for…

This paper presents a simple yet effective approach that improves continual test-time adaptation (TTA) in a memory-efficient manner. TTA may primarily be conducted on edge devices with limited memory, so reducing memory is crucial but has…

Recent advances in video reward models and post-training strategies have improved text-to-video (T2V) generation. While these models typically assess visual quality, motion quality, and text alignment, they often overlook key structural…

Text understanding often suffers from domain shifts. To handle testing domains, domain adaptation (DA) is trained to adapt to a fixed and observed testing domain; a more challenging paradigm, test-time adaptation (TTA), cannot access the…

We propose a new two-stage pre-training framework for video-to-text generation tasks such as video captioning and video question answering: A generative encoder-decoder model is first jointly pre-trained on massive image-text data to learn…

It is encouraged to see that progress has been made to bridge videos and natural language. However, mainstream video captioning methods suffer from slow inference speed due to the sequential manner of autoregressive decoding, and prefer…

The recent advance in vision-language models is largely attributed to the abundance of image-text data. We aim to replicate this success for video-language models, but there simply is not enough human-curated video-text data available. We…

Test-Time Adaptation (TTA) for black-box models accessible only via APIs remains a largely unexplored challenge. Existing approaches such as post-hoc output refinement offer limited adaptive capacity, while Zeroth-Order Optimization (ZOO)…

Test-time domain adaptation aims to adapt a source pre-trained model to a target domain without using any source data. Existing works mainly consider the case where the target domain is static. However, real-world machine perception systems…

Recent video text spotting methods usually require the three-staged pipeline, i.e., detecting text in individual images, recognizing localized text, tracking text streams with post-processing to generate final results. These methods…

Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained…

Most current captioning systems use language models trained on data from specific settings, such as image-based captioning via Amazon Mechanical Turk, limiting their ability to generalize to other modality distributions and contexts. This…

Cross-modal retrieval between videos and texts has gained increasing research interest due to the rapid emergence of videos on the web. Generally, a video contains rich instance and event information and the query text only describes a part…

Vision and Language Models (VLMs), such as CLIP, have enabled visual recognition of a potentially unlimited set of categories described by text prompts. However, for the best visual recognition performance, these models still require tuning…

Instructional videos are a common source for learning text-video or even multimodal representations by leveraging subtitles extracted with automatic speech recognition systems (ASR) from the audio signal in the videos. However, in contrast…

Due to the impressive zero-shot capabilities, pre-trained vision-language models (e.g. CLIP), have attracted widespread attention and adoption across various domains. Nonetheless, CLIP has been observed to be susceptible to adversarial…

Vision-language models (VLMs) such as CLIP and Grounding DINO have achieved remarkable success in object recognition and detection. However, their performance often degrades under real-world distribution shifts. Test-time adaptation (TTA)…

Recently, Automatic Speech Recognition (ASR) systems (e.g., Whisper) have achieved remarkable accuracy improvements but remain highly sensitive to real-world unseen data (data with large distribution shifts), including noisy environments…

Current test-time adaptation (TTA) approaches aim to adapt a machine learning model to environments that change continuously. Yet, it is unclear whether TTA methods can maintain their adaptability over prolonged periods. To answer this…

Prior works have demonstrated zero-shot text-to-speech by using a generative language model on audio tokens obtained via a neural audio codec. It is still challenging, however, to adapt them to low-latency scenarios. In this paper, we…

Recent text-to-video generation approaches rely on computationally heavy training and require large-scale video datasets. In this paper, we introduce a new task of zero-shot text-to-video generation and propose a low-cost approach (without…