Related papers: Compressed Video Aggregator: Content-driven Module…
Although learned video compression methods have exhibited outstanding performance, most of them typically follow a hybrid coding paradigm that requires explicit motion estimation and compensation, resulting in a complex solution for video…
Multimodal sentiment analysis has a wide range of applications due to its information complementarity in multimodal interactions. Previous works focus more on investigating efficient joint representations, but they rarely consider the…
Recent cutting-edge feature aggregation paradigms for video object detection rely on inferring feature correspondence. The feature correspondence estimation problem is fundamentally difficult due to poor image quality, motion blur, etc, and…
This paper investigates the role of CLIP image embeddings within the Stable Video Diffusion (SVD) framework, focusing on their impact on video generation quality and computational efficiency. Our findings indicate that CLIP embeddings,…
The development of video large multimodal models (LMMs) has been hindered by the difficulty of curating large amounts of high-quality raw data from the web. To address this, we propose an alternative approach by creating a high-quality…
Semi-supervised video object segmentation is a fundamental yet Challenging task in computer vision. Embedding matching based CFBI series networks have achieved promising results by foreground-background integration approach. Despite its…
We introduce a novel cost aggregation network, dubbed Volumetric Aggregation with Transformers (VAT), to tackle the few-shot segmentation task by using both convolutions and transformers to efficiently handle high dimensional correlation…
Streaming video understanding with large vision-language models (VLMs) requires a compact memory that can support future reasoning over an ever-growing visual history. A common solution is to compress the key-value (KV) cache, but existing…
This paper presents FluxMem, a training-free framework for efficient streaming video understanding. FluxMem adaptively compresses redundant visual memory through a hierarchical, two-stage design: (1) a Temporal Adjacency Selection (TAS)…
In recent years, transformer-based methods have achieved remarkable progress in medical image segmentation due to their superior ability to capture long-range dependencies. However, these methods typically suffer from two major limitations.…
The proliferation of video-on-demand (VOD) services has led to a paradox of choice, overwhelming users with vast content libraries and revealing limitations in current recommender systems. This research introduces a novel approach by…
The rapid increase in the amount of published visual data and the limited time of users bring the demand for processing untrimmed videos to produce shorter versions that convey the same information. Despite the remarkable progress that has…
Over the past decade, the online video industry has greatly expanded the volume of visual data that is streamed and shared over the Internet. Moreover, because of the increasing ease of video capture, many millions of consumers create and…
We introduce a novel generative model for video prediction based on latent flow matching, an efficient alternative to diffusion-based models. In contrast to prior work, we keep the high costs of modeling the past during training and…
Recent advances in training-free video editing have enabled lightweight and precise cross-frame generation by leveraging pre-trained text-to-image diffusion models. However, existing methods often rely on heuristic frame selection to…
There has been a growing trend in compressing and transmitting videos from terminals for machine vision tasks. Nevertheless, most video coding optimization method focus on minimizing distortion according to human perceptual metrics,…
Crowd flow segmentation is an important step in many video surveillance tasks. In this work, we propose an algorithm for segmenting flows in H.264 compressed videos in a completely unsupervised manner. Our algorithm works on motion vectors…
Video summarization methods are usually classified into shot-level or frame-level methods, which are individually used in a general way. This paper investigates the underlying complementarity between the frame-level and shot-level methods,…
Learned video compression methods have demonstrated great promise in catching up with traditional video codecs in their rate-distortion (R-D) performance. However, existing learned video compression schemes are limited by the binding of the…
In Video Object Detection (VID), a common practice is to leverage the rich temporal contexts from the video to enhance the object representations in each frame. Existing methods treat the temporal contexts obtained from different objects…