Related papers: Dynamic Computational Time for Visual Attention

Recurrent neural networks (RNNs) have been used extensively and with increasing success to model various types of sequential data. Much of this progress has been achieved through devising recurrent units and architectures with the…

RRAM crossbars have been studied to construct in-memory accelerators for neural network applications due to their in-situ computing capability. However, prior RRAM-based accelerators show efficiency degradation when executing the popular…

In this paper we propose to augment a modern neural-network architecture with an attention model inspired by human perception. Specifically, we adversarially train and analyze a neural model incorporating a human inspired, visual attention…

Hardware support for deep convolutional neural networks (CNNs) is critical to advanced computer vision in mobile and embedded devices. Current designs, however, accelerate generic CNNs; they do not exploit the unique characteristics of…

Graph convolutional networks (GCNs) have been very successful in modeling non-Euclidean data structures, like sequences of body skeletons forming actions modeled as spatio-temporal graphs. Most GCN-based action recognition methods use deep…

We present a reward-predictive, model-based deep learning method featuring trajectory-constrained visual attention for local planning in visual navigation tasks. Our method learns to place visual attention at locations in latent image space…

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…

Deep convolutional neural networks (CNNs) have made impressive progress in many video recognition tasks such as video pose estimation and video object detection. However, CNN inference on video is computationally expensive due to processing…

The meteoric rise in the adoption of deep neural networks as computational models of vision has inspired efforts to "align" these models with humans. One dimension of interest for alignment includes behavioral choices, but moving beyond…

Sequential recommendation aims to recommend the next item of users' interest based on their historical interactions. Recently, the self-attention mechanism has been adapted for sequential recommendation, and demonstrated state-of-the-art…

The computational demands of self-attention mechanisms pose a critical challenge for transformer-based video generation, particularly in synthesizing ultra-long sequences. Current approaches, such as factorized attention and fixed sparse…

This paper proposes a deep learning architecture based on Residual Network that dynamically adjusts the number of executed layers for the regions of the image. This architecture is end-to-end trainable, deterministic and problem-agnostic.…

This paper addresses the problem of efficiently achieving visual predictive control tasks. To this end, a memory of motion, containing a set of trajectories built off-line, is used for leveraging precomputation and dealing with difficult…

Current approaches for activity recognition often ignore constraints on computational resources: 1) they rely on extensive feature computation to obtain rich descriptors on all frames, and 2) they assume batch-mode access to the entire test…

Attention mechanisms and non-local mean operations in general are key ingredients in many state-of-the-art deep learning techniques. In particular, the Transformer model based on multi-head self-attention has recently achieved great success…

Deep learning models, in particular \textit{image} models, have recently gained generalisability and robustness. %are becoming more general and robust by the day. In this work, we propose to exploit such advances in the realm of…

Deep learning's success has been attributed to the training of large, overparameterized models on massive amounts of data. As this trend continues, model training has become prohibitively costly, requiring access to powerful computing…

Human actions captured in video sequences contain two crucial factors for action recognition, i.e., visual appearance and motion dynamics. To model these two aspects, Convolutional and Recurrent Neural Networks (CNNs and RNNs) are adopted…

Auto-regressive (AR) models, initially successful in language generation, have recently shown promise in visual generation tasks due to their superior sampling efficiency. Unlike image generation, video generation requires a substantially…

Action visual tempo characterizes the dynamics and the temporal scale of an action, which is helpful to distinguish human actions that share high similarities in visual dynamics and appearance. Previous methods capture the visual tempo…