Related papers: EKO: Adaptive Sampling of Compressed Video Data
Video large language models (Video-LLMs) face high computational costs due to large volumes of visual tokens. Existing token compression methods typically adopt a two-stage spatiotemporal compression strategy, relying on stage-specific…
Video compression is a fundamental topic in the visual intelligence, bridging visual signal sensing/capturing and high-level visual analytics. The broad success of artificial intelligence (AI) technology has enriched the horizon of video…
It is challenging for reinforcement learning (RL) algorithms to succeed in real-world applications like financial trading and logistic system due to the noisy observation and environment shifting between training and evaluation. Thus, it…
Long-form video understanding presents unique challenges that extend beyond traditional short-video analysis approaches, particularly in capturing long-range dependencies, processing redundant information efficiently, and extracting…
Video dataset condensation aims to reduce the immense computational cost of video processing. However, it faces a fundamental challenge regarding the inseparable interdependence between spatial appearance and temporal dynamics. Prior work…
This paper studies the computational offloading of video action recognition in edge computing. To achieve effective semantic information extraction and compression, following semantic communication we propose a novel spatiotemporal…
Accurate traffic congestion classification requires models that jointly capture roadway scene context and non-stationary traffic motion, yet most prior work treats these requirements in isolation. Vision-based methods often depend on…
It is always a challenging problem to deliver a huge volume of videos over the Internet. To meet the high bandwidth and stringent playback demand, one feasible solution is to cache video contents on edge servers based on predicted video…
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…
Video dimensions are continuously increasing to provide more realistic and immersive experiences to global streaming and social media viewers. However, increments in video parameters such as spatial resolution and frame rate are inevitably…
Steered-Mixtures-of Experts (SMoE) present a unified framework for sparse representation and compression of image data with arbitrary dimensionality. Recent work has shown great improvements in the performance of such models for image and…
Large-scale video-language pre-training has made remarkable strides in advancing video-language understanding tasks. However, the heavy computational burden of video encoding remains a formidable efficiency bottleneck, particularly for…
Many machine learning models, such as logistic regression~(LR) and support vector machine~(SVM), can be formulated as composite optimization problems. Recently, many distributed stochastic optimization~(DSO) methods have been proposed to…
Despite recent interest and advances in facial micro-expression research, there is still plenty room for improvement in terms of micro-expression recognition. Conventional feature extraction approaches for micro-expression video consider…
Downsampling is one of the most basic image processing operations. Improper spatio-temporal downsampling applied on videos can cause aliasing issues such as moir\'e patterns in space and the wagon-wheel effect in time. Consequently, the…
Token pruning has emerged as a mainstream approach for developing efficient Video Large Language Models (Video LLMs). This work revisits and advances the two predominant token-pruning paradigms: attention-based selection and…
In many mobile visual analysis applications, compressed video is transmitted over a communication network and analyzed by a server. Typical processing steps performed at the server include keypoint detection, descriptor calculation, and…
The main contributions of this paper are twofold: First, we present an in-depth analysis of the impact of frame rate reductions on the visual quality of the video and the encoding as well as decoding energy. Second, we propose a lightweight…
While most frames in long-form video are redundant, the critical information resides in temporal surprises: moments where the actual visual features deviate from their predicted evolution. Inspired by the human brain's predictive coding, we…
Most multi-objective optimisation algorithms maintain an archive explicitly or implicitly during their search. Such an archive can be solely used to store high-quality solutions presented to the decision maker, but in many cases may…