Related papers: Context-Aware Iteration Policy Network for Efficie…

With increasing share of renewables in power generation mix, system operators would need to run Optimal Power Flow (OPF) problems closer to real-time to better manage uncertainty. Given that OPF is an expensive optimization problem to…

We present a framework to use recently introduced Capsule Networks for solving the problem of Optical Flow, one of the fundamental computer vision tasks. Most of the existing state of the art deep architectures either uses a correlation…

Most recent diffusion-based methods still show a large gap compared to non-diffusion methods for video frame interpolation, in both accuracy and efficiency. Most of them formulate the problem as a denoising procedure in latent space…

Temporal interaction networks capture the history of activities between entities along a timeline. At each interaction, some quantity of data (money, information, kbytes, etc.) flows from one vertex of the network to another. Flow-based…

For an autonomous vehicle it is essential to observe the ongoing dynamics of a scene and consequently predict imminent future scenarios to ensure safety to itself and others. This can be done using different sensors and modalities. In this…

Event-based cameras are raising interest within the computer vision community. These sensors operate with asynchronous pixels, emitting events, or "spikes", when the luminance change at a given pixel since the last event surpasses a certain…

Multi-turn interaction remains challenging for online reinforcement learning. A common solution is trajectory-level optimization, which treats each trajectory as a single training sample. However, this approach can be inefficient and yield…

Optical flow estimation is an important yet challenging problem in the field of video analytics. The features of different semantics levels/layers of a convolutional neural network can provide information of different granularity. To…

Recent work showed that hybrid networks, which combine predefined and learnt filters within a single architecture, are more amenable to theoretical analysis and less prone to overfitting in data-limited scenarios. However, their performance…

Optical flow techniques are becoming increasingly performant and robust when estimating motion in a scene, but their performance has yet to be proven in the area of facial expression recognition. In this work, a variety of optical flow…

3D scene flow estimation is a vital tool in perceiving our environment given depth or range sensors. Unlike optical flow, the data is usually sparse and in most cases partially occluded in between two temporal samplings. Here we propose a…

Accurate short-term streamflow and flood forecasting are critical for mitigating river flood impacts, especially given the increasing climate variability. Machine learning-based streamflow forecasting relies on large streamflow datasets…

Network pruning is one of the most dominant methods for reducing the heavy inference cost of deep neural networks. Existing methods often iteratively prune networks to attain high compression ratio without incurring significant loss in…

Modern large displacement optical flow algorithms usually use an initialization by either sparse descriptor matching techniques or dense approximate nearest neighbor fields. While the latter have the advantage of being dense, they have the…

Recent weakly-supervised methods for scene flow estimation from LiDAR point clouds are limited to explicit reasoning on object-level. These methods perform multiple iterative optimizations for each rigid object, which makes them vulnerable…

Optical flow estimation remains challenging due to untextured areas, motion boundaries, occlusions, and more. Thus, the estimated flow is not equally reliable across the image. To that end, post-hoc confidence measures have been introduced…

The Information Plane is a conceptual framework used to analyze the flow of information in neural networks, but traditional methods based on activations may not fully capture the dynamics of information processing. This paper introduces a…

Data-centric learning emphasizes curating high-quality training samples to boost performance rather than designing new architectures. A central problem is to estimate the influence of training sample efficiently. Prior studies largely focus…

In this paper, we propose a convolutional layer inspired by optical flow algorithms to learn motion representations. Our representation flow layer is a fully-differentiable layer designed to capture the `flow' of any representation channel…

The proposed RMS-FlowNet is a novel end-to-end learning-based architecture for accurate and efficient scene flow estimation which can operate on point clouds of high density. For hierarchical scene flow estimation, the existing methods…