Related papers: Patch-based Object-centric Transformers for Effici…
The emergence of Diffusion Transformers (DiT) has brought significant advancements to video generation, especially in text-to-video and image-to-video tasks. Although video generation is widely applied in various fields, most existing…
As multi-object tracking (MOT) tasks continue to evolve toward more general and multi-modal scenarios, the rigid and task-specific architectures of existing MOT methods increasingly hinder their applicability across diverse tasks and limit…
A prevalent approach in Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViT) involves freezing the majority of the backbone parameters and solely learning low-rank adaptation weight matrices to accommodate…
Open-vocabulary multi-object tracking (OVMOT) represents a critical new challenge involving the detection and tracking of diverse object categories in videos, encompassing both seen categories (base classes) and unseen categories (novel…
We propose a novel Transformer-based architecture for the task of generative modelling of 3D human motion. Previous work commonly relies on RNN-based models considering shorter forecast horizons reaching a stationary and often implausible…
Vision Transformers (ViTs) are built on the assumption of treating image patches as ``visual tokens" and learn patch-to-patch attention. The patch embedding based tokenizer has a semantic gap with respect to its counterpart, the textual…
With the increasing importance of video data in real-world applications, there is a rising need for efficient object detection methods that utilize temporal information. While existing video object detection (VOD) techniques employ various…
Recent Diffusion Transformers (DiTs) have shown impressive capabilities in generating high-quality single-modality content, including images, videos, and audio. However, it is still under-explored whether the transformer-based diffuser can…
The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing. This paper presents a novel framework named Point Cloud Transformer(PCT) for point cloud learning. PCT is based on…
While today's video recognition systems parse snapshots or short clips accurately, they cannot connect the dots and reason across a longer range of time yet. Most existing video architectures can only process <5 seconds of a video without…
Action recognition models have achieved impressive results by incorporating scene-level annotations, such as objects, their relations, 3D structure, and more. However, obtaining annotations of scene structure for videos requires a…
Recently, DETR and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors. However, their performance on…
Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks, while the self-attention computation in Transformer scales quadratically w.r.t. the input patch number. Thus, existing solutions commonly…
While the Transformer architecture has become ubiquitous in the machine learning field, its adaptation to 3D shape recognition is non-trivial. Due to its quadratic computational complexity, the self-attention operator quickly becomes…
Humans are remarkably good at understanding and reasoning about complex visual scenes. The capability to decompose low-level observations into discrete objects allows us to build a grounded abstract representation and identify the…
Panoramic video generation aims to synthesize 360-degree immersive videos, holding significant importance in the fields of VR, world models, and spatial intelligence. Existing works fail to synthesize high-quality panoramic videos due to…
Multiple object tracking (MOT) has been successfully investigated in computer vision. However, MOT for the videos captured by unmanned aerial vehicles (UAV) is still challenging due to small object size, blurred object appearance, and very…
High-fidelity video generation remains challenging for diffusion models due to the difficulty of modeling complex spatio-temporal dynamics efficiently. Recent video diffusion methods typically represent a video as a sequence of…
Autoregressive models have shown superior performance and efficiency in image generation, but remain constrained by high computational costs and prolonged training times in video generation. In this study, we explore methods to accelerate…
Annotating 3D data remains a costly bottleneck for 3D object detection, motivating the development of weakly supervised annotation methods that rely on more accessible 2D box annotations. However, relying solely on 2D boxes introduces…