Related papers: Denoise to Track: Harnessing Video Diffusion Prior…

Transformer-based visual trackers have demonstrated significant progress owing to their superior modeling capabilities. However, existing trackers are hampered by low speed, limiting their applicability on devices with limited computational…

Diffusion Transformers (DiTs) have shown remarkable performance in generating high-quality videos. However, the quadratic complexity of 3D full attention remains a bottleneck in scaling DiT training, especially with high-definition, lengthy…

Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transformer (ViT) has also demonstrated strong modeling capabilities…

Diffusion Transformers (DiT) have emerged as a widely adopted backbone for high-fidelity image and video generation, yet their iterative denoising process incurs high computational costs. Existing training-free acceleration methods rely on…

Zero-shot, training-free, image-based text-to-video generation is an emerging area that aims to generate videos using existing image-based diffusion models. Current methods in this space require specific architectural changes to image…

Video-based human-object interaction (HOI) understanding requires both detecting ongoing interactions and anticipating their future evolution. However, existing methods usually treat anticipation as a downstream forecasting task built on…

Achieving highly accurate and real-time 3D occupancy prediction from cameras is a critical requirement for the safe and practical deployment of autonomous vehicles. While this shift to sparse 3D representations solves the encoding…

Dense object tracking, the ability to localize specific object points with pixel-level accuracy, is an important computer vision task with numerous downstream applications in robotics. Existing approaches either compute dense keypoint…

In recent years, diffusion models have demonstrated remarkable success in high-fidelity image synthesis. However, fine-tuning these models for specialized domains, such as medical imaging, remains challenging due to limited domain-specific…

With the widespread use of online social media platforms, information diffusion has become a prevalent phenomenon, making Information Diffusion Prediction (IDP) increasingly important for various applications. Despite significant…

Foundation models have emerged as powerful tools across various domains including language, vision, and multimodal tasks. While prior works have addressed unsupervised image segmentation, they significantly lag behind supervised models. In…

Diffusion Transformers (DiTs) excel at generation, but their global self-attention makes controllable, reference-image-based editing a distinct challenge. Unlike U-Nets, naively injecting local appearance into a DiT can disrupt its holistic…

Most modern multiple object tracking (MOT) systems follow the tracking-by-detection paradigm, consisting of a detector followed by a method for associating detections into tracks. There is a long history in tracking of combining motion and…

Training deep learning models for video classification from audio-visual data commonly requires immense amounts of labeled training data collected via a costly process. A challenging and underexplored, yet much cheaper, setup is few-shot…

Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur. Previous approaches exploit to propagate and aggregate features across…

Recent progress in diffusion models has significantly advanced the field of human image animation. While existing methods can generate temporally consistent results for short or regular motions, significant challenges remain, particularly…

Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified…

This paper introduces DrDiff, a novel framework for long-text generation that overcomes the efficiency-quality trade-off through three core technologies. First, we design a dynamic expert scheduling mechanism that intelligently allocates…

Recent tracking-by-detection approaches use deep object detectors as target detection baseline, because of their high performance on still images. For effective video object tracking, object detection is integrated with a data association…

Prevalent human-object interaction (HOI) detection approaches typically leverage large-scale visual-linguistic models to help recognize events involving humans and objects. Though promising, models trained via contrastive learning on…