Related papers: SOTFormer: A Minimal Transformer for Unified Objec…
Efficient video action recognition remains a challenging problem. One large model after another takes the place of the state-of-the-art on the Kinetics dataset, but real-world efficiency evaluations are often lacking. In this work, we fill…
We propose the task Future Object Detection, in which the goal is to predict the bounding boxes for all visible objects in a future video frame. While this task involves recognizing temporal and kinematic patterns, in addition to the…
The rich spatio-temporal information is crucial to capture the complicated target appearance variations in visual tracking. However, most top-performing tracking algorithms rely on many hand-crafted components for spatio-temporal…
Capturing the dependencies between joints is critical in skeleton-based action recognition task. Transformer shows great potential to model the correlation of important joints. However, the existing Transformer-based methods cannot capture…
Predicting the future behavior of agents is a fundamental task in autonomous vehicle domains. Accurate prediction relies on comprehending the surrounding map, which significantly regularizes agent behaviors. However, existing methods have…
Most recent transformer-based models show impressive performance on vision tasks, even better than Convolution Neural Networks (CNN). In this work, we present a novel, flexible, and effective transformer-based model for high-quality…
Understanding dynamics from visual observations is a challenging problem that requires disentangling individual objects from the scene and learning their interactions. While recent object-centric models can successfully decompose a scene…
In this paper, we consider the problem of long-term point tracking, which requires consistent identification of points across multiple frames in a video, despite changes in appearance, lighting, perspective, and occlusions. We target online…
Single-object tracking is a well-known and challenging research topic in computer vision. Over the last two decades, numerous researchers have proposed various algorithms to solve this problem and achieved promising results. Recently,…
Persistent multi-object tracking (MOT) allows autonomous vehicles to navigate safely in highly dynamic environments. One of the well-known challenges in MOT is object occlusion when an object becomes unobservant for subsequent frames. The…
Long-term time series forecasting (LTSF) has been widely applied in finance, traffic prediction, and other domains. Recently, patch-based transformers have emerged as a promising approach, segmenting data into sub-level patches that serve…
In the past few years, time series foundation models have achieved superior predicting accuracy. However, real-world time series often exhibit significant diversity in their temporal patterns across different time spans and domains, making…
Multi-person motion prediction remains a challenging problem, especially in the joint representation learning of individual motion and social interactions. Most prior methods only involve learning local pose dynamics for individual motion…
Transformer-based architectures achieved breakthrough performance in natural language processing and computer vision, yet they remain inferior to simpler linear baselines in multivariate long-term forecasting. To better understand this…
Traditional vision-based autonomous driving systems often face difficulties in navigating complex environments when relying solely on single-image inputs. To overcome this limitation, incorporating temporal data such as past image frames or…
Single object tracking aims to localize target object with specific reference modalities (bounding box, natural language or both) in a sequence of specific video modalities (RGB, RGB+Depth, RGB+Thermal or RGB+Event.). Different reference…
The deployment of transformers for visual object tracking has shown state-of-the-art results on several benchmarks. However, the transformer-based models are under-utilized for Siamese lightweight tracking due to the computational…
The speed-precision trade-off is a critical problem for visual object tracking which usually requires low latency and deployment on constrained resources. Existing solutions for efficient tracking mainly focus on adopting light-weight…
Research in efficient vision backbones is evolving into models that are a mixture of convolutions and transformer blocks. A smart combination of both, architecture-wise and component-wise is mandatory to excel in the speedaccuracy…
Temporal information is crucial for visual tracking, but existing multi-frame trackers are vulnerable to model drift caused by naively aggregating noisy historical predictions. In this paper, we introduce DTPTrack, a lightweight and…