11 accepted papers
The automatic recognition of surgical steps is essential for enhancing situational awareness and workflow automation in robotic-assisted surgery. However, existing vision-based approaches exhibit limitations in effectively leveraging rich spatial-temporal information from surgical videos, particular
As the tenth part of the third-generation AVS standard series for real-time speech coding, AVS3P10 is the recent standard completed in the Audio Video Coding Standards Workgroup of China (AVS). Combining the state-of-the-art deep generative networks and signal processing methods, AVS3P10 targets def…
Model-based reinforcement learning (RL) offers a solution to the data inefficiency that plagues most model-free RL algorithms. However, learning a robust world model often requires complex and deep architectures, which are computationally expensive and challenging to train. Within the world model, s…
In recent years, Text-to-Image (T2I) models have made remarkable advancements, yet accurate accurate association of attributes remains a key challenge. This paper presents FreeAlign, a novel training-free framework designed to enhance attribute alignment in T2I generation. By modulating attention an…
Given a complex text description, existing studies have indeed made significant progress in motion synthesis, which largely overlook the fine-grained action information from expressive texts. In this paper, we introduce LGDDM, a LLM-Guided Dual-branch Diffusion Model, which relies on the LLM’s abili…
Diffusion denoising models have great potential in generating diverse and realistic human motions. However, despite the impressive performance of existing methods, they still face some issues. The diffusion process often significantly overlooks physical laws, leading to physically implausible motion…
The unlimited sampling framework, utilizing modulo analog-to-digital converters (ADCs), has recently been introduced to mitigate the information loss caused by the dynamic range limitations of traditional ADCs. In this paper, we evaluate the noise sensitivity of unlimited sampling in line spectral e…
Although diffusion models advance condition-based visual generation, they suffer from speed and cost issues, unlike faster AutoRegressive methods that are limited in performance. To address these, we introduce the Stable Control Visual AutoRegressive Model (SCVAR). SCVAR ensures stable control by al…
Diffusion models excel at audio-driven gesture generation. However, the reverse denoising process is computationally intensive and time-redundant. Additionally, existing methods predominantly focus on the quality and diversity of upper-body gestures, without considering the movement trajectories of…
Dynamic scheduling of access to shared resources by autonomous systems is a challenging problem, characterized as being NP-hard. The complexity of this task leads to a combinatorial explosion of possibilities in highly dynamic systems where arriving requests must be continuously scheduled subject to…
In direction-of-arrival (DOA) estimation, both stochastic and deterministic priors of source signals have been used to localize more sources than sensors. The stochastic prior refers to uncorrelateness of sources, while the deterministic one includes the constant modulus (CM) property of sources. Ex…