Related papers: EvRepSL: Event-Stream Representation via Self-Supe…
Object tracking based on retina-inspired and event-based dynamic vision sensor (DVS) is challenging for the noise events, rapid change of event-stream shape, chaos of complex background textures, and occlusion. To address these challenges,…
Achieving streaming, fine-grained control over the outputs of autoregressive video diffusion models remains challenging, making it difficult to ensure that they consistently align with user expectations. To bridge this gap, we propose…
With the rapid development of deep learning, video deraining has experienced significant progress. However, existing video deraining pipelines cannot achieve satisfying performance for scenes with rain layers of complex spatio-temporal…
The underwater domain presents a vast array of challenges for roboticists and computer vision researchers alike, such as poor lighting conditions and high dynamic range scenes. In these adverse conditions, traditional vision techniques…
Road segmentation is pivotal for autonomous vehicles, yet achieving low latency and low compute solutions using frame based cameras remains a challenge. Event cameras offer a promising alternative. To leverage their low power sensing, we…
In event-based sensing, many sensors independently and asynchronously emit events when there is a change in their input. Event-based sensing can present significant improvements in power efficiency when compared to traditional sampling,…
Event-based sensors offer high temporal resolution and low latency by generating sparse, asynchronous data. However, converting this irregular data into dense tensors for use in standard neural networks diminishes these inherent advantages,…
Devising intelligent agents able to live in an environment and learn by observing the surroundings is a longstanding goal of Artificial Intelligence. From a bare Machine Learning perspective, challenges arise when the agent is prevented…
Learning visual representations through self-supervision is an extremely challenging task as the network needs to sieve relevant patterns from spurious distractors without the active guidance provided by supervision. This is achieved…
As the use of neuromorphic, event-based vision sensors expands, the need for compression of their output streams has increased. While their operational principle ensures event streams are spatially sparse, the high temporal resolution of…
Self-supervised learning aims to learn representation that can be effectively generalized to downstream tasks. Many self-supervised approaches regard two views of an image as both the input and the self-supervised signals, assuming that…
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…
Self-supervised learning (SSL), as a newly emerging unsupervised representation learning paradigm, generally follows a two-stage learning pipeline: 1) learning invariant and discriminative representations with auto-annotation pretext(s),…
Event cameras are emerging imaging technology that offers advantages over conventional frame-based imaging sensors in dynamic range and sensing speed. Complementing the rich texture and color perception of traditional image frames, the…
Event cameras are considered to have great potential for computer vision and robotics applications because of their high temporal resolution and low power consumption characteristics. However, the event stream output from event cameras has…
Video data is highly expressive and has traditionally been very difficult for a machine to interpret. Querying event patterns from video streams is challenging due to its unstructured representation. Middleware systems such as Complex Event…
Visual speech recognition (VSR), commonly known as lip reading, has garnered significant attention due to its wide-ranging practical applications. The advent of deep learning techniques and advancements in hardware capabilities have…
Conventional vision-language models (VLMs) struggle to interpret scenes captured under adverse conditions (e.g., low light, high dynamic range, or fast motion) because standard RGB images degrade in such environments. Event cameras provide…
Traditionally, video is structured as a sequence of discrete image frames. Recently, however, a novel video sensing paradigm has emerged which eschews video frames entirely. These "event" sensors aim to mimic the human vision system with…
Video super-resolution (VSR) technology excels in reconstructing low-quality video, avoiding unpleasant blur effect caused by interpolation-based algorithms. However, vast computation complexity and memory occupation hampers the edge of…