相关论文: Approximate Query Service on Autonomous IoT Camera…
Good temporal representations are crucial for video understanding, and the state-of-the-art video recognition framework is based on two-stream networks. In such framework, besides the regular ConvNets responsible for RGB frame inputs, a…
Wilderness monitoring tasks, such as poaching surveillance and forest fire detection, require pervasive and high-accuracy sensing. While AIoT offers a promising path, covering vast, inaccessible regions necessitates the massive deployment…
Visual servoing technology has been well developed and applied in many automated manufacturing tasks, especially in tools' pose alignment. To access a full global view of tools, most applications adopt eye-to-hand configuration or…
Optical flow estimation is a crucial subfield of computer vision, serving as a foundation for video tasks. However, the real-world robustness is limited by animated synthetic datasets for training. This introduces domain gaps when applied…
Event-based cameras are novel, efficient sensors inspired by the human vision system, generating an asynchronous, pixel-wise stream of data. Learning from such data is generally performed through heavy preprocessing and event integration…
Convolutional Architecture for Fast Feature Encoding (CAFFE) [11] is a software package for the training, classifying, and feature extraction of images. The UCF Sports Action dataset is a widely used machine learning dataset that has 200…
State-of-the-art machine-learning methods for event cameras treat events as dense representations and process them with conventional deep neural networks. Thus, they fail to maintain the sparsity and asynchronous nature of event data,…
There is an increasing consensus that the design and optimization of low light image enhancement methods need to be fully driven by perceptual quality. With numerous approaches proposed to enhance low-light images, much less work has been…
Massive frame redundancy and limited context window make efficient frame selection crucial for long-video understanding with large vision-language models (LVLMs). Prevailing approaches, however, adopt a flat sampling paradigm which treats…
Streaming video understanding demands more than watching longer videos: assistants must decide when to speak in real time, balancing responsiveness against verbosity. Yet most video-language models (VideoLLMs) are trained for offline…
Event cameras provide a compelling alternative to traditional frame-based sensors, capturing dynamic scenes with high temporal resolution and low latency. Moving objects trigger events with precise timestamps along their trajectory,…
We present a video summarization approach for egocentric or "wearable" camera data. Given hours of video, the proposed method produces a compact storyboard summary of the camera wearer's day. In contrast to traditional keyframe selection…
Video synopsis, summarizing a video to generate a shorter video by exploiting the spatial and temporal redundancies, is important for surveillance and archiving. Existing trajectory-based video synopsis algorithms will not able to work in…
Learning from videos offers a promising path toward generalist robots by providing rich visual and temporal priors beyond what real robot datasets contain. While existing video generative models produce impressive visual predictions, they…
We are interested in counting the number of instances of object classes in natural, everyday images. Previous counting approaches tackle the problem in restricted domains such as counting pedestrians in surveillance videos. Counts can also…
Displaying near-real-time traffic information is a useful feature of digital navigation maps. However, most commercial providers rely on privacy-compromising measures such as deriving location information from cellphones to estimate…
Scene flow is a challenging task aimed at jointly estimating the 3D structure and motion of the sensed environment. Although deep learning solutions achieve outstanding performance in terms of accuracy, these approaches divide the whole…
Scaling video diffusion transformers is fundamentally bottlenecked by two compounding costs: the expensive quadratic complexity of attention per step, and the iterative sampling steps. In this work, we propose EFlow, an efficient few-step…
We present a unifying framework to solve several computer vision problems with event cameras: motion, depth and optical flow estimation. The main idea of our framework is to find the point trajectories on the image plane that are best…
The state of the art in video understanding suffers from two problems: (1) The major part of reasoning is performed locally in the video, therefore, it misses important relationships within actions that span several seconds. (2) While there…