Related papers: RipViz: Finding Rip Currents by Learning Pathline …
Predicting high dimensional video sequences is a curiously difficult problem. The number of possible futures for a given video sequence grows exponentially over time due to uncertainty. This is especially evident when trying to predict…
We propose to combine the active vortex generators with the particle image velocimetry (PIV) measurements and post-processing streamwise vortex characterization algorithms into a feedback based closed-loop control system for wind turbine…
Visual repetition is ubiquitous in our world. It appears in human activity (sports, cooking), animal behavior (a bee's waggle dance), natural phenomena (leaves in the wind) and in urban environments (flashing lights). Estimating visual…
Real-time motion detection in non-stationary scenes is a difficult task due to dynamic background, changing foreground appearance and limited computational resource. These challenges degrade the performance of the existing methods in…
Imagining multiple consecutive frames given one single snapshot is challenging, since it is difficult to simultaneously predict diverse motions from a single image and faithfully generate novel frames without visual distortions. In this…
Successive frames of a video are highly redundant, and the most popular object detection methods do not take advantage of this fact. Using multiple consecutive frames can improve detection of small objects or difficult examples and can…
There is lots of scientific work about object detection in images. For many applications like for example autonomous driving the actual data on which classification has to be done are videos. This work compares different methods, especially…
Despite recent progress, video diffusion models still struggle to synthesize realistic videos involving highly dynamic motions or requiring fine-grained motion controllability. A central limitation lies in the scarcity of such examples in…
Around 1930 Ludwig Prandtl and his colleagues O. Tietjens and W. M\"uller published two films with visualizations of flows around surface piercing obstacles to illustrate the unsteady process of flow separation. These visualizations were…
In this paper, we consider the task of unsupervised object discovery in videos. Previous works have shown promising results via processing optical flows to segment objects. However, taking flow as input brings about two drawbacks. First,…
Live animation has gained immense popularity for enhancing online engagement, yet achieving high-quality, real-time, and stable animation with diffusion models remains challenging, especially on consumer-grade GPUs. Existing methods…
We propose a lightweight and accurate method for detecting anomalies in videos. Existing methods used multiple-instance learning (MIL) to determine the normal/abnormal status of each segment of the video. Recent successful researches argue…
This thesis is part of a CIFRE agreement between the company Othello and the LIASD laboratory. The objective is to develop an artificial intelligence system that can detect real-time dangers in a video stream. To achieve this, a novel…
This paper introduces a novel methodology for generating fast and memory-efficient video continuations. Our method, dubbed FlowC2S, fine-tunes a pre-trained text-to-video flow model to learn a vector field between the current and succeeding…
Existing methods to recognize actions in static images take the images at their face value, learning the appearances---objects, scenes, and body poses---that distinguish each action class. However, such models are deprived of the rich…
We consider the problem of estimating repetition in video, such as performing push-ups, cutting a melon or playing violin. Existing work shows good results under the assumption of static and stationary periodicity. As realistic video is…
Existing methods for video-based person re-identification (ReID) mainly learn the appearance feature of a given pedestrian via a feature extractor and a feature aggregator. However, the appearance models would fail when different…
Motion plays a crucial role in understanding videos and most state-of-the-art neural models for video classification incorporate motion information typically using optical flows extracted by a separate off-the-shelf method. As the…
In this paper, we are concerned with the detection of progressive dynamic saliency from video sequences. More precisely, we are interested in saliency related to motion and likely to appear progressively over time. It can be relevant to…
Despite the great progress in video understanding made by deep convolutional neural networks, feature representation learned by existing methods may be biased to static visual cues. To address this issue, we propose a novel method to…