Related papers: SweetTok: Semantic-Aware Spatial-Temporal Tokenize…
Spatially dense self-supervised learning is a rapidly growing problem domain with promising applications for unsupervised segmentation and pretraining for dense downstream tasks. Despite the abundance of temporal data in the form of videos,…
Traditional video codecs optimized for pixel fidelity collapse at ultra-low bitrates and produce severe artifacts. This failure arises from a fundamental misalignment between pixel accuracy and human perception. We propose a semantic video…
In this paper, we present LLaVA-Scissor, a training-free token compression strategy designed for video multimodal large language models. Previous methods mostly attempt to compress tokens based on attention scores, but fail to effectively…
Most Neural Video Codecs (NVCs) only employ temporal references to generate temporal-only contexts and latent prior. These temporal-only NVCs fail to handle large motions or emerging objects due to limited contexts and misaligned latent…
Large Audio Language Models (LALMs) have emerged with strong performance across diverse audio understanding tasks and can be further enhanced by neural audio codecs. Transitioning from multi-layer residual vector quantizers to a…
In low-level video analyses, effective representations are important to derive the correspondences between video frames. These representations have been learned in a self-supervised fashion from unlabeled images or videos, using carefully…
Detecting deepfake videos is highly challenging given the complexity of characterizing spatio-temporal artifacts. Most existing methods rely on binary classifiers trained using real and fake image sequences, therefore hindering their…
The core challenge in video understanding lies in perceiving dynamic content changes over time. However, multimodal large language models struggle with temporal-sensitive video tasks, which requires generating timestamps to mark the…
Large language models have drastically changed the prospects of AI by introducing technologies for more complex natural language processing. However, current methodologies to train such LLMs require extensive resources including but not…
Text-video retrieval is a challenging cross-modal task, which aims to align visual entities with natural language descriptions. Current methods either fail to leverage the local details or are computationally expensive. What's worse, they…
Unpaired video-to-video translation aims to translate videos between a source and a target domain without the need of paired training data, making it more feasible for real applications. Unfortunately, the translated videos generally suffer…
Real-time semantic video segmentation is a challenging task due to the strict requirements of inference speed. Recent approaches mainly devote great efforts to reducing the model size for high efficiency. In this paper, we rethink this…
We present AToken, the first unified visual tokenizer that achieves both high-fidelity reconstruction and semantic understanding across images, videos, and 3D assets. Unlike existing tokenizers that specialize in either reconstruction or…
Deepfakes are AI-generated media in which the original content is digitally altered to create convincing but manipulated images, videos, or audio. Among the various types of deepfakes, lip-syncing deepfakes are one of the most challenging…
People see text. Humans read by recognizing words as visual objects, including their shapes, layouts, and patterns, before connecting them to meaning, which enables us to handle typos, distorted fonts, and various scripts effectively.…
Segmenting objects with complex shapes, such as wires, bicycles, or structural grids, remains a significant challenge for current segmentation models, including the Segment Anything Model (SAM) and its high-quality variant SAM-HQ. These…
Encoding videos into discrete tokens could align with text tokens to facilitate concise and unified multi-modal LLMs, yet introducing significant spatiotemporal compression compared to continuous video representation. Previous discrete…
Weakly-supervised temporal action localization aims to locate action regions and identify action categories in untrimmed videos simultaneously by taking only video-level labels as the supervision. Pseudo label generation is a promising…
Streaming Video Large Language Models (VideoLLMs) have demonstrated impressive performance across various video understanding tasks, but they face significant challenges in real-time deployment due to the high computational cost of…
This paper proposes a novel transformer-based framework that aims to enhance weakly supervised semantic segmentation (WSSS) by generating accurate class-specific object localization maps as pseudo labels. Building upon the observation that…