Related papers: TESPEC: Temporally-Enhanced Self-Supervised Pretra…
Deep convolutional networks have achieved great success for visual recognition in still images. However, for action recognition in videos, the advantage over traditional methods is not so evident. This paper aims to discover the principles…
Event cameras output event streams as sparse, asynchronous data with microsecond-level temporal resolution, enabling visual perception with low latency and a high dynamic range. While existing Multimodal Large Language Models (MLLMs) have…
State-of-the-art saliency prediction methods develop upon model architectures or loss functions; while training to generate one target saliency map. However, publicly available saliency prediction datasets can be utilized to create more…
Event cameras harness advantages such as low latency, high temporal resolution, and high dynamic range (HDR), compared to standard cameras. Due to the distinct imaging paradigm shift, a dominant line of research focuses on event-to-video…
Recurrent Networks are one of the most powerful and promising artificial neural network algorithms to processing the sequential data such as natural languages, sound, time series data. Unlike traditional feed-forward network, Recurrent…
Current Deep Learning methods for environment segmentation and velocity estimation rely on Convolutional Recurrent Neural Networks to exploit spatio-temporal relationships within obtained sensor data. These approaches derive scene dynamics…
Event cameras provide an advantage over traditional frame-based cameras when capturing fast-moving objects without a motion blur. They achieve this by recording changes in light intensity (known as events), thus allowing them to operate at…
Inspired by the recent success of sequence modeling in RL and the use of masked language model for pre-training, we propose a masked model for pre-training in RL, RePreM (Representation Pre-training with Masked Model), which trains the…
Event cameras are novel bio-inspired sensors that capture motion dynamics with much higher temporal resolution than traditional cameras, since pixels react asynchronously to brightness changes. They are therefore better suited for tasks…
Event-based cameras are dynamic vision sensors that provide asynchronous measurements of changes in per-pixel brightness at a microsecond level. This makes them significantly faster than conventional frame-based cameras, and an appealing…
Event-based vision sensors provide significant advantages for high-speed perception, including microsecond temporal resolution, high dynamic range, and low power consumption. When combined with Spiking Neural Networks (SNNs), they can be…
Leveraging the high temporal resolution and dynamic range, object detection with event cameras can enhance the performance and safety of automotive and robotics applications in real-world scenarios. However, processing sparse event data…
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,…
Reconstructing intensity frames from event data while maintaining high temporal resolution and dynamic range is crucial for bridging the gap between event-based and frame-based computer vision. Previous approaches have depended on…
Due to the large memory footprint of untrimmed videos, current state-of-the-art video localization methods operate atop precomputed video clip features. These features are extracted from video encoders typically trained for trimmed action…
Recently, vision model pre-training has evolved from relying on manually annotated datasets to leveraging large-scale, web-crawled image-text data. Despite these advances, there is no pre-training method that effectively exploits the…
Video-language pre-trained models have shown remarkable success in guiding video question-answering (VideoQA) tasks. However, due to the length of video sequences, training large-scale video-based models incurs considerably higher costs…
We present two approaches that use unlabeled data to improve sequence learning with recurrent networks. The first approach is to predict what comes next in a sequence, which is a conventional language model in natural language processing.…
Temporal action segmentation in untrimmed videos has gained increased attention recently. However, annotating action classes and frame-wise boundaries is extremely time consuming and cost intensive, especially on large-scale datasets. To…
Accelerator-based neutrino physics is entering an energy-frontier regime in which interactions reach the TeV scale and produce exceptionally dense, overlapping detector signatures. In this regime, event interpretation becomes impractical…