Related papers: SRVP: Strong Recollection Video Prediction Model U…
Vision-Language-Action (VLA) models offer a unified framework for robotic perception and control, but their ability to scale to real-world, long-horizon tasks is limited by the high computational cost of attention and the large memory…
Deep learning based image Super-Resolution (SR) has shown rapid development due to its ability of big data digestion. Generally, deeper and wider networks can extract richer feature maps and generate SR images with remarkable quality.…
Recurrent neural networks (RNNs) have shown the ability to improve scene parsing through capturing long-range dependencies among image units. In this paper, we propose dense RNNs for scene labeling by exploring various long-range semantic…
Awareness detection technologies have been gaining traction in a variety of enterprises; most often used for driver fatigue detection, recent research has shifted towards using computer vision technologies to analyze user attention in…
Much of recent Deep Reinforcement Learning success is owed to the neural architecture's potential to learn and use effective internal representations of the world. While many current algorithms access a simulator to train with a large…
Event-based object detection has gained increasing attention due to its advantages such as high temporal resolution, wide dynamic range, and asynchronous address-event representation. Leveraging these advantages, Spiking Neural Networks…
Successful video analysis relies on accurate recognition of pixels across frames, and frame reconstruction methods based on video correspondence learning are popular due to their efficiency. Existing frame reconstruction methods, while…
Vision-Language Models (VLMs) often yield inconsistent descriptions of the same object across viewpoints, hindering the ability of embodied agents to construct consistent semantic representations over time. Previous methods resolved…
Spiking Neural Networks (SNNs) are at the forefront of neuromorphic computing thanks to their potential energy-efficiency, low latencies, and capacity for continual learning. While these capabilities are well suited for robotics tasks, SNNs…
Vision-language pre-training (VLP) has attracted increasing attention recently. With a large amount of image-text pairs, VLP models trained with contrastive loss have achieved impressive performance in various tasks, especially the…
The estimation of implicit cross-frame correspondences and the high computational cost have long been major challenges in video semantic segmentation (VSS) for driving scenes. Prior works utilize keyframes, feature propagation, or…
Neural attention (NA) has become a key component of sequence-to-sequence models that yield state-of-the-art performance in as hard tasks as abstractive document summarization (ADS) and video captioning (VC). NA mechanisms perform inference…
We tackle the long-term prediction of scene evolution in a complex downtown scenario for automated driving based on Lidar grid fusion and recurrent neural networks (RNNs). A bird's eye view of the scene, including occupancy and velocity, is…
Audio data, often synchronized with video frames, plays a crucial role in guiding the audience's visual attention. Incorporating audio information into video saliency prediction tasks can enhance the prediction of human visual behavior.…
Reference features from a template or historical frames are crucial for visual object tracking. Prior works utilize all features from a fixed template or memory for visual object tracking. However, due to the dynamic nature of videos, the…
Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining consistent object segmentation due to temporal context variability and the presence of other visually similar objects. We propose an end-to-end R-VOS…
In visual planning (VP), an agent learns to plan goal-directed behavior from observations of a dynamical system obtained offline, e.g., images obtained from self-supervised robot interaction. Most previous works on VP approached the problem…
Computational models of vision have traditionally been developed in a bottom-up fashion, by hierarchically composing a series of straightforward operations - i.e. convolution and pooling - with the aim of emulating simple and complex cells…
Space-time video super-resolution (STVSR) aims to construct a high space-time resolution video sequence from the corresponding low-frame-rate, low-resolution video sequence. Inspired by the recent success to consider spatial-temporal…
Traditional visual place recognition (VPR), usually using standard cameras, is easy to fail due to glare or high-speed motion. By contrast, event cameras have the advantages of low latency, high temporal resolution, and high dynamic range,…