Related papers: Space-Time Attention with Shifted Non-Local Search
Non-local patch based methods were until recently state-of-the-art for image denoising but are now outperformed by CNNs. Yet they are still the state-of-the-art for video denoising, as video redundancy is a key factor to attain high…
Video Moment Retrieval (VMR) is a task to localize the temporal moment in untrimmed video specified by natural language query. For VMR, several methods that require full supervision for training have been proposed. Unfortunately, acquiring…
We present new refinement heuristics for the balanced graph partitioning problem that break with an age-old rule. Traditionally, local search only permits moves that keep the block sizes balanced (below a size constraint). In this work, we…
In this work, we conduct a systematic analysis of Native Sparse Attention (NSA) and propose targeted improvements that enhance long-context modeling. A key insight is that alternating between local (sliding-window) and global (compression,…
Attention mechanisms, which enable a neural network to accurately focus on all the relevant elements of the input, have become an essential component to improve the performance of deep neural networks. There are mainly two attention…
In this paper, we present a so-called interlaced sparse self-attention approach to improve the efficiency of the \emph{self-attention} mechanism for semantic segmentation. The main idea is that we factorize the dense affinity matrix as the…
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,…
Sparse attention methods exploit the inherent sparsity in attention to speed up the prefilling phase of long-context inference, mitigating the quadratic complexity of full attention computation. While existing sparse attention methods rely…
Performing a real-time and accurate instrument segmentation from videos is of great significance for improving the performance of robotic-assisted surgery. We identify two important clues for surgical instrument perception, including local…
Automatically discovering composable abstractions from raw perceptual data is a long-standing challenge in machine learning. Recent slot-based neural networks that learn about objects in a self-supervised manner have made exciting progress…
Video object segmentation is challenging due to the factors like rapidly fast motion, cluttered backgrounds, arbitrary object appearance variation and shape deformation. Most existing methods only explore appearance information between two…
The cost-effective visual representation and fast query-by-example search are two challenging goals that should be maintained for web-scale visual retrieval tasks on moderate hardware. This paper introduces a fast and robust method that…
Video object segmentation is a fundamental research problem in computer vision. Recent techniques have often applied attention mechanism to object representation learning from video sequences. However, due to temporal changes in the video…
Video Moment Retrieval, which aims to locate in-context video moments according to a natural language query, is an essential task for cross-modal grounding. Existing methods focus on enhancing the cross-modal interactions between all…
In this paper, we introduce the spatial bias to learn global knowledge without self-attention in convolutional neural networks. Owing to the limited receptive field, conventional convolutional neural networks suffer from learning long-range…
In video denoising, the adjacent frames often provide very useful information, but accurate alignment is needed before such information can be harnassed. In this work, we present a multi-alignment network, which generates multiple flow…
We improve reliable, long-horizon, goal-directed navigation in partially-mapped environments by using non-locally available information to predict the goodness of temporally-extended actions that enter unseen space. Making predictions about…
Deep learning has achieved great success in video recognition, yet still struggles to recognize novel actions when faced with only a few examples. To tackle this challenge, few-shot action recognition methods have been proposed to transfer…
Previous methods based on 3DCNN, convLSTM, or optical flow have achieved great success in video salient object detection (VSOD). However, they still suffer from high computational costs or poor quality of the generated saliency maps. To…
Supernet is a core component in many recent Neural Architecture Search (NAS) methods. It not only helps embody the search space but also provides a (relative) estimation of the final performance of candidate architectures. Thus, it is…