Search Results

Since the introduction of player positional tracking data to the NBA in 2013, the field of basketball analytics has been steadily developing. As such, more and more teams utilize data-driven approaches to maximize the potential for their team to score a ...

Generative models are now widely used by graphic designers and artists. Prior works have shown that these models remember and often replicate content from their training data during generation. Hence as their proliferation increases, it has become ...

Diffusion models have proven to be state-of-the-art methods for generative tasks. These models involve training a U-Net to iteratively predict and remove noise, and the resulting model can synthesize high-fidelity, diverse, novel images. However, ...

Image customization has been extensively studied in text-to-image (T2I) diffusion models, leading to impressive outcomes and applications. With the emergence of text-to-video (T2V) diffusion models, its temporal counterpart, motion customization, ...

Implicit Neural Networks (INRs) have emerged as powerful representations to encode all forms of data, including images, videos, audios, and scenes. With video, many INRs for video have been proposed for the compression task, and recent methods ...

Recently, 3D Gaussian splatting (3D-GS) has gained popularity in novel-view scene synthesis. It addresses the challenges of lengthy training times and slow rendering speeds associated with Neural Radiance Fields (NeRFs). Through rapid, ...$$

Neural Radiance Fields (NeRFs) have revolutionized the reconstruction of static scenes and objects in 3D, offering unprecedented quality. However, extending NeRFs to model dynamic objects or object articulations remains a challenging problem. ...

We propose a simple yet effective approach for few-shot action recognition, emphasizing the disentanglement of motion and appearance representations. By harnessing recent progress in tracking, specifically point trajectories and self-supervised ...

Despite the abundant availability and content richness for video data, its high-dimensionality poses challenges for video research. Recent advancements have explored the implicit representation for videos using neural networks, demonstrating ...${\mathbf{}}^{\mathbf{}}$$\mathbf{}$$\mathbf{}$$\mathbf{}$

We present a simple self-supervised method to enhance the performance of ViT features for dense downstream tasks. Our Lightweight Feature Transform (LiFT) is a straightforward and compact postprocessing network that can be applied to enhance the ...

In this paper, we present a novel robust framework for low-level vision tasks, including denoising, object removal, frame interpolation, and super-resolution, that does not require any external training data corpus. Our proposed approach directly learns ...

Egocentric vision holds great promise for increasing access to visual information and improving the quality of life for blind people. While we strive to improve recognition performance, it remains difficult to identify which object is of interest to the ...

We present Neural Space-filling Curves (SFCs), a data-driven approach to infer a context-based scan order for a set of images. Linear ordering of pixels forms the basis for many applications such as video scrambling, compression, and auto-...

In the context of online privacy, many methods propose complex security preserving measures to protect sensitive data. In this paper we note that: not storing any sensitive data is the best form of security. We propose an online framework called “...

We study recognizing attributes for objects in visual scenes. We consider attributes to be any phrases that describe an object’s physical and semantic properties, and its relationships with other objects. Existing work studies attribute prediction ...

Finding dense semantic correspondence is a fundamental problem in computer vision, which remains challenging in complex scenes due to background clutter, extreme intra-class variation, and a severe lack of ground truth. In this paper, we aim to ...

We study a referential game (a type of signaling game) where two agents communicate with each other via a discrete bottleneck to achieve a common goal. In our referential game, the goal of the speaker is to compose a message or a symbolic representation ...

We propose a novel neural representation for videos (NeRV) which encodes videos in neural networks. Unlike conventional representations that treat videos as frame sequences, we represent videos as neural networks taking frame index as input. Given a ...

In this paper, we address the task of interacting with dynamic environments where the changes in the environment are independent of the agent. We study this through the context of trapping a moving ball with a UR5 robotic arm. Our key contribution is an ...

The JPEG image compression algorithm is the most popular method of image compression because of it’s ability for large compression ratios. However, to achieve such high compression, information is lost. For aggressive quantization settings, this ...