相关论文: FrameExit: Conditional Early Exiting for Efficient…

Transferring image-based object detectors to the domain of video remains challenging under resource constraints. Previous efforts utilised optical flow to allow unchanged features to be propagated, however, the overhead is considerable when…

In this paper, Gated-ViGAT, an efficient approach for video event recognition, utilizing bottom-up (object) information, a new frame sampling policy and a gating mechanism is proposed. Specifically, the frame sampling policy uses weighted…

Deploying deep learning models in time-critical applications with limited computational resources, for instance in edge computing systems and IoT networks, is a challenging task that often relies on dynamic inference methods such as early…

We introduce the task of early mistake detection in video, where the goal is to determine whether a keystep in a procedural activity is performed correctly while observing as little of the streaming video as possible. To tackle this…

Large-scale Transformer models bring significant improvements for various downstream vision language tasks with a unified architecture. The performance improvements come with increasing model size, resulting in slow inference speed and…

Diffusion models have shown remarkable performance in generation problems over various domains including images, videos, text, and audio. A practical bottleneck of diffusion models is their sampling speed, due to the repeated evaluation of…

Action recognition is computationally expensive. In this paper, we address the problem of frame selection to improve the accuracy of action recognition. In particular, we show that selecting good frames helps in action recognition…

This work addresses the need for a balanced approach between performance and efficiency in scalable production environments for visually-rich document understanding (VDU) tasks. Currently, there is a reliance on large document foundation…

In recent years, Vision-Language Models (VLMs) have shown remarkable performance improvements in Vision-Language tasks. However, their large size poses challenges for real-world applications where inference latency is a concern. To tackle…

Existing video captioning approaches typically require to first sample video frames from a decoded video and then conduct a subsequent process (e.g., feature extraction and/or captioning model learning). In this pipeline, manual frame…

We propose a very simple and efficient video compression framework that only focuses on modeling the conditional entropy between frames. Unlike prior learning-based approaches, we reduce complexity by not performing any form of explicit…

In this paper, we propose a framework named OCSampler to explore a compact yet effective video representation with one short clip for efficient video recognition. Recent works prefer to formulate frame sampling as a sequential decision task…

This paper presents LiteEval, a simple yet effective coarse-to-fine framework for resource efficient video recognition, suitable for both online and offline scenarios. Exploiting decent yet computationally efficient features derived at a…

Training an effective video action recognition model poses significant computational challenges, particularly under limited resource budgets. Current methods primarily aim to either reduce model size or utilize pre-trained models, limiting…

Recently, the efficient deployment and acceleration of powerful vision transformers (ViTs) on resource-limited edge devices for providing multimedia services have become attractive tasks. Although early exiting is a feasible solution for…

Recently,there has been a lot of interest in building compact models for video classification which have a small memory footprint (<1 GB). While these models are compact, they typically operate by repeated application of a small weight…

Videos are multimodal in nature. Conventional video recognition pipelines typically fuse multimodal features for improved performance. However, this is not only computationally expensive but also neglects the fact that different videos rely…

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…

Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a possible solution, but it may degrade the recognition…

Enabling efficient text-video retrieval on edge-end devices is critical for real-world applications. Yet, existing methods face a critical challenge in balancing accuracy and computational efficiency: uniform frame sampling methods ensure…