Related papers: ResQ: Residual Quantization for Video Perception

Visual place recognition is a critical task in computer vision, especially for localization and navigation systems. Existing methods often rely on contrastive learning: image descriptors are trained to have small distance for similar images…

Recent trends in Video Instance Segmentation (VIS) have seen a growing reliance on online methods to model complex and lengthy video sequences. However, the degradation of representation and noise accumulation of the online methods,…

Recently, 3D convolutional networks (3D ConvNets) yield good performance in action recognition. However, optical flow stream is still needed to ensure better performance, the cost of which is very high. In this paper, we propose a fast but…

Single image super-resolution (SISR) aims to reconstruct a high-resolution image from its low-resolution observation. Recent deep learning-based SISR models show high performance at the expense of increased computational costs, limiting…

Deep neural networks have been proven effective in a wide range of tasks. However, their high computational and memory costs make them impractical to deploy on resource-constrained devices. To address this issue, quantization schemes have…

Video Snapshot Compressive Imaging (SCI) aims to use a low-speed 2D camera to capture high-speed scene as snapshot compressed measurements, followed by a reconstruction algorithm to reconstruct the high-speed video frames. State-of-the-art…

In the recent noisy intermediate-scale quantum era, the research on the combination of artificial intelligence and quantum computing has been greatly developed. Inspired by neural networks, developing quantum neural networks with specific…

State-of-the-art systems for semantic image segmentation use feed-forward pipelines with fixed computational costs. Building an image segmentation system that works across a range of computational budgets is challenging and time-intensive…

In the field of video analytics, particularly traffic surveillance, there is a growing need for efficient and effective methods for processing and understanding video data. Traditional full video decoding techniques can be computationally…

We present RePOSE, a fast iterative refinement method for 6D object pose estimation. Prior methods perform refinement by feeding zoomed-in input and rendered RGB images into a CNN and directly regressing an update of a refined pose. Their…

Neural networks have established as a generic and powerful means to approach challenging problems such as image classification, object detection or decision making. Their successful employment foots on an enormous demand of compute. The…

Video super-resolution aims at generating a high-resolution video from its low-resolution counterpart. With the rapid rise of deep learning, many recently proposed video super-resolution methods use convolutional neural networks in…

Text-based 3D motion generation aims to automatically synthesize diverse motions from natural-language descriptions to extend user creativity, whereas motion editing modifies an existing motion sequence in response to text while preserving…

We propose an approach to learn spatio-temporal features in videos from intermediate visual representations we call "percepts" using Gated-Recurrent-Unit Recurrent Networks (GRUs).Our method relies on percepts that are extracted from all…

Post-training quantization (PTQ) of large language models (LLMs) holds the promise in reducing the prohibitive computational cost at inference time. Quantization of all weight, activation and key-value (KV) cache tensors to 4-bit without…

Modern video codecs and learning-based approaches struggle for semantic reconstruction at extremely low bit-rates due to reliance on low-level spatiotemporal redundancies. Generative models, especially diffusion models, offer a new paradigm…

Recurrent neural networks have achieved excellent performance in many applications. However, on portable devices with limited resources, the models are often too large to deploy. For applications on the server with large scale concurrent…

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…

Recovering temporally consistent 3D human body pose, shape and motion from a monocular video is a challenging task due to (self-)occlusions, poor lighting conditions, complex articulated body poses, depth ambiguity, and limited availability…

There are many tasks within video compression which require fast bit rate estimation. As an example, rate-control algorithms are only feasible because it is possible to estimate the required bit rate without needing to encode the entire…