9 accepted papers
With the rapid rise of social media and Internet culture, memes have become a popular medium for expressing emotional tendencies. This has sparked growing interest in Meme Emotion Understanding (MEU), which aims to classify the emotional intent behind memes by leveraging their multimodal contents. W
Recently, deep multi-agent reinforcement learning (MARL) has demonstrated promising performance for solving challenging tasks, such as long-term dependencies and non-Markovian environments. Its success is partly attributed to conditioning policies on large fixed context length. However, such large f…
Model merging is a widespread technology in large language models (LLMs) that integrates multiple task-specific LLMs into a unified one, enabling the merged model to inherit the specialized capabilities of these LLMs. Most task-specific LLMs are sourced from open-source communities and have not unde…
This paper proposes a safety critical nonlinear model predictive control (NMPC) to track a target in an obstacle-existing scene for a car-like robot with a limited detection ability. A temporary artificial reference within the detection region is employed as a temporary target to reduce the meaningl
The accurate assessment of sperm morphology is crucial in andrological diagnostics, where the segmentation of sperm images presents significant challenges. Existing approaches frequently rely on large annotated datasets and often struggle with the segmentation of overlapping sperm and the presence o…
Navigation through crowded human environments is challenging for social robots. While reinforcement learning has been adopted for its capacity to capture complex interactions, the training process often relies on simulators to replicate realistic crowd behaviors, ensuring cost-efficiency. Existing c…
This letter addresses the problem of designing an interception strategy for an underactuated uncrewed surface vessel (USV) in the presence of uncertain external disturbances and unknown internal parameters i.e., linear and nonlinear damping coefficients, vehicle mass, etc. The interception strategy
Rich semantics inside an image result in its ambiguous relationship with others, i.e., two images could be similar in one condition but dissimilar in another. Given triplets like "aircraft" is similar to "bird" than "train", Weakly Supervised Conditional Similarity Learning (WS-CSL) learns multiple…
Deep learning models have achieved great success in supervised shape descriptor learning for 3D shape retrieval, classification, and correspondence. However, the unsupervised shape descriptor calculated via deep learning is less studied than that of supervised ones due to the design challenges of un…