23 accepted papers
Cross-time vehicle re-identification (Re-ID), especially across day and night conditions, remains a challenging problem due to drastic illumination variations that lead to significant domain shifts. While existing methods perform well under daytime scenarios, their effectiveness degrades severely in
Existing multimodal representation learning approaches often rely on simple feature concatenation or unified transformations, which fail to effectively disentangle and leverage common and private information across different modalities in a progressive manner. Moreover, they typically lack adaptive
Relational Deep Learning aims to learn directly on multi-table databases, yet current methods face a fundamental tension: Transformers' quadratic complexity prohibits the large contexts relational data demands, while GNNs sacrifice global context for efficiency. We introduce Ramba, the first selecti…
Balancing performance trade-off on long-tail data distributions remains a long-standing challenge. In this paper, we posit that this dilemma stems from a phenomenon called "tail performance degradation" in continual learning (the model tends to severely overfit on head classes while quickly forgetti
Large Language Models (LLMs) show remarkable semantic understanding but often struggle with structural understanding when processing graph topologies in a serialized format. Existing solutions rely on training external graph-based adapters or fine-tuning, which incur high costs and lost generalizabi…
The rapid development of vision language models (VLMs) demands rigorous and reliable evaluation. However, current visual question answering (VQA) benchmarks often depend on open-ended questions, making accurate evaluation difficult due to the variability in natural language responses. To address thi…
Text watermarking for Large Language Models (LLMs) has made significant progress in detecting LLM outputs and preventing misuse. Current watermarking techniques offer high detectability, minimal impact on text quality, and robustness to text editing. However, current researches lack investigati…
Multimodal sarcasm detection (MSD) leverages multimodal data, including both images and text, to detect whether the input content contains sarcastic information. Despite recent advances, existing MSD approaches often overlook the imbalance in sarcastic content between text and image modalities, wher…
Text-driven human motion generation has attracted considerable critical attention in recent years. The task requires generating movements that are diverse, natural, and comfortable in accordance with the text description. However, while generating the human motion, there is a significant gap in the…
CLIP outperforms self-supervised models like DINO as vision encoders for vision-language models (VLMs), but it remains unclear whether this advantage stems from CLIP’s language supervision or its much larger training data. To disentangle these factors, we pre-train CLIP and DINO under controlled set
Large Language Models (LLMs) have demonstrated notable capabilities across various tasks, showcasing complex problem-solving abilities. Understanding and executing complex rules, along with multi-step planning, are fundamental to logical reasoning and critical for practical LLM agents and decision-m…
Negation is a fundamental linguistic phenomenon that can entirely reverse the meaning of a sentence. As vision language models (VLMs) continue to advance and are deployed in high-stakes applications, assessing their ability to comprehend negation becomes essential. To address this, we introduce NegV…
The Pre-trained Speech Models (PSMs) generate universal speech representations using self-supervised or weakly-supervised learning from large-scale datasets. It achieves promising performance when fine-tuned for specific tasks such as Speech Emotion Recognition (SER). However, fine-tuning on various…
Scene text image super-resolution aims to enhance low-resolution, spatially distorted text images by reconstructing high-resolution counterparts with clear textual structure and superior visual fidelity. Nevertheless, the prevalence of multi-line text in real-world scenarios presents a significant c…
Diffusion-Based Purification (DBP) has emerged as an effective defense mechanism against adversarial attacks. The success of DBP is often attributed to the forward diffusion process, which reduces the distribution gap between clean and adversarial images by adding Gaussian noise. Although this expla…
In multimodal human-computer interaction, generating co-speech gestures is crucial for enhancing interaction naturalness and user experience. However, achieving synchronized and natural gesture sequences remains a significant challenge due to the complexity of modeling temporal dependencies across d…
Instruction following is one of the fundamental capabilities of large language models (LLMs). As the ability of LLMs is constantly improving, they have been increasingly applied to deal with complex human instructions in real-world scenarios. Therefore, how to evaluate the ability of complex instruc…
"In autonomous simulation and surveillance, realistic scenarios are crucial for advancing object detection algorithms. Existing aerial datasets suffer from sample class imbalance, especially in larger vehicles like trucks, and unrealistic lighting conditions. This hampers progress in driving behavio…
To enhance the integration of robots into daily human life and industrial settings, there is a growing focus on the development of robots capable of physical collaboration with humans. Studies have shown that haptic feedback serves as an essential channel of communication that allows humans to bette
Blur was naturally analyzed in the frequency domain, by estimating the latent sharp image and the blur kernel given a blurry image. Recent progress on image deblurring always designs end-to-end architectures and aims at learning the difference between blurry and sharp image pairs from pixel-level, w…
Deep learning models are emerging to summarize source code to comment, facilitating tasks of code documentation and program comprehension. Scaled-up large language models trained on large open corpus have achieved good performance in such tasks. However, in practice, the subject code in one ce…
In this paper, a deep learning network with double closed-loop structure is introduced to tackle the image deblurring problem. The first closed-loop in our model is composed of two networks which learn a pair of opposite mappings between the blurry and sharp images. By this way, the solution spaces…
We address the problem of synthesizing new video frames in an existing video, either in-between existing frames (interpolation), or subsequent to them (extrapolation). This problem is challenging because video appearance and motion can be highly complex. Traditional optical-flow-based solutions ofte…