Related papers: Unsupervised Video Decomposition using Spatio-temp…
Due to the complex and highly dynamic motions in the real world, synthesizing dynamic videos from multi-view inputs for arbitrary viewpoints is challenging. Previous works based on neural radiance field or 3D Gaussian splatting are limited…
This work presents advancements in multi-class vehicle detection using UAV cameras through the development of spatiotemporal object detection models. The study introduces a Spatio-Temporal Vehicle Detection Dataset (STVD) containing 6, 600…
We focus on the task of future frame prediction in video governed by underlying physical dynamics. We work with models which are object-centric, i.e., explicitly work with object representations, and propagate a loss in the latent space.…
The goal of self-supervised visual representation learning is to learn strong, transferable image representations, with the majority of research focusing on object or scene level. On the other hand, representation learning at part level has…
Self-supervised representation learning is able to learn semantically meaningful features; however, much of its recent success relies on multiple crops of an image with very few objects. Instead of learning view-invariant representation…
Recent adaptive methods for efficient video recognition mostly follow the two-stage paradigm of "preview-then-recognition" and have achieved great success on multiple video benchmarks. However, this two-stage paradigm involves two visits of…
We propose a method for unsupervised video object segmentation by transferring the knowledge encapsulated in image-based instance embedding networks. The instance embedding network produces an embedding vector for each pixel that enables…
Deep learning models have enjoyed great success for image related computer vision tasks like image classification and object detection. For video related tasks like human action recognition, however, the advancements are not as significant…
The objective of this paper is self-supervised representation learning, with the goal of solving semi-supervised video object segmentation (a.k.a. dense tracking). We make the following contributions: (i) we propose to improve the existing…
This paper introduces an unsupervised framework to extract semantically rich features for video representation. Inspired by how the human visual system groups objects based on motion cues, we propose a deep convolutional neural network that…
Modeling the dynamic behavior of deformable objects is crucial for creating realistic digital worlds. While conventional simulations produce high-quality motions, their computational costs are often prohibitive. Subspace simulation…
Detecting objects in 3D LiDAR data is a core technology for autonomous driving and other robotics applications. Although LiDAR data is acquired over time, most of the 3D object detection algorithms propose object bounding boxes…
The transmission matrix (TM) is a representation to describe the light scattering process through a scattering medium. The degree of control elements in TM is correlated with the capacity of evaluating enormous equations with tremendous…
Most model-free visual object tracking methods formulate the tracking task as object location estimation given by a 2D segmentation or a bounding box in each video frame. We argue that this representation is limited and instead propose to…
We propose a new "Unbiased through Textual Description (UTD)" video benchmark based on unbiased subsets of existing video classification and retrieval datasets to enable a more robust assessment of video understanding capabilities. Namely,…
Successful video analysis relies on accurate recognition of pixels across frames, and frame reconstruction methods based on video correspondence learning are popular due to their efficiency. Existing frame reconstruction methods, while…
Temporal modeling is crucial for video super-resolution. Most of the video super-resolution methods adopt the optical flow or deformable convolution for explicitly motion compensation. However, such temporal modeling techniques increase the…
We propose a self-supervised spatio-temporal matching method, coined Motion-Aware Mask Propagation (MAMP), for video object segmentation. MAMP leverages the frame reconstruction task for training without the need for annotations. During…
In this paper, we develop a new approach of spatially supervised recurrent convolutional neural networks for visual object tracking. Our recurrent convolutional network exploits the history of locations as well as the distinctive visual…
Humans make extensive use of vision and touch as complementary senses, with vision providing global information about the scene and touch measuring local information during manipulation without suffering from occlusions. While prior work…