Related papers: DeformTrace: A Deformable State Space Model with R…
As one of the prominent AI-generated content, Deepfake has raised significant safety concerns. Although it has been demonstrated that temporal consistency cues offer better generalization capability, existing methods based on CNNs…
Speculative decoding is a technique to leverage hardware concurrency in order to enable multiple steps of token generation in a single forward pass, thus improving the efficiency of large-scale autoregressive (AR) Transformer models.…
Time Delay Neural Networks (TDNNs) are widely used in both DNN-HMM based hybrid speech recognition systems and recent end-to-end systems. Nevertheless, the receptive fields of TDNNs are limited and fixed, which is not desirable for tasks…
Deepfake detection remains highly challenging, particularly in cross-dataset scenarios and complex real-world settings. This challenge mainly arises because artifact patterns vary substantially across different forgery methods, whereas…
The emergence of artificial intelligence-generated content (AIGC) has raised concerns about the authenticity of multimedia content in various fields. However, existing research for forgery content detection has focused mainly on binary…
Diffusion Language Models (DLMs) enable parallel decoding via iterative denoising, where remasking strategies play a critical role in balancing inference speed and output quality. Existing methods predominantly rely on static confidence…
Recently, deep-learning-based approaches have been widely studied for deformable image registration task. However, most efforts directly map the composite image representation to spatial transformation through the convolutional neural…
Federated learning (FL) is emerging as a promising technique for collaborative learning without local data leaving their devices. However, clients' data originating from diverse domains may degrade model performance due to domain shifts,…
Computed tomography (CT) imaging could be very practical for diagnosing various diseases. However, the nature of the CT images is even more diverse since the resolution and number of the slices of a CT scan are determined by the machine and…
With advanced image journaling tools, one can easily alter the semantic meaning of an image by exploiting certain manipulation techniques such as copy-clone, object splicing, and removal, which mislead the viewers. In contrast, the…
DETR-based methods, which use multi-layer transformer decoders to refine object queries iteratively, have shown promising performance in 3D indoor object detection. However, the scene point features in the transformer decoder remain fixed,…
Detecting deepfake videos is highly challenging given the complexity of characterizing spatio-temporal artifacts. Most existing methods rely on binary classifiers trained using real and fake image sequences, therefore hindering their…
Diffusion large language models (dLLMs) generate text through iterative denoising. In commonly adopted parallel decoding schemes, each step confirms only high-confidence positions while remasking the others. By analyzing dLLM denoising…
Monocular SLAM algorithms perform robustly when observing rigid scenes, however, they fail when the observed scene deforms, for example, in medical endoscopy applications. We present DefSLAM, the first monocular SLAM capable of operating in…
Efficiently modeling spatio-temporal (ST) physical processes and observations presents a challenging problem for the deep learning community. Many recent studies have concentrated on meticulously reconciling various advantages, leading to…
Recent advances in transformer-based lightweight object tracking have established new standards across benchmarks, leveraging the global receptive field and powerful feature extraction capabilities of attention mechanisms. Despite these…
Video-Language Models (VLMs), powered by the advancements in Large Language Models (LLMs), are charting new frontiers in video understanding. A pivotal challenge is the development of an efficient method to encapsulate video content into a…
We investigated domain adaptive semantic segmentation in foggy weather scenarios, which aims to enhance the utilization of unlabeled foggy data and improve the model's adaptability to foggy conditions. Current methods rely on clear images…
Manipulating deformable objects is a ubiquitous task in household environments, demanding adequate representation and accurate dynamics prediction due to the objects' infinite degrees of freedom. This work proposes DeformNet, which utilizes…
Today, state-of-the-art deep neural networks that process event-camera data first convert a temporal window of events into dense, grid-like input representations. As such, they exhibit poor generalizability when deployed at higher inference…