18 accepted papers
The emergence of Large Audio-Language Models (LALMs) has advanced Speech Emotion Recognition (SER), but their size limits deployment in resource-constrained environments. While Knowledge Distillation is effective for LALM compression, existing methods remain underexplored in distilling the cross-mod…
Approximately 445.2 million individuals worldwide are living with traumatic amputations, and an estimated 31.64 million children aged 0–14 have congenital limb differences, yet they remain largely underrepresented in human pose estimation (HPE) research. Accurate HPE could significantly benefit this…
This paper presents Reed-Solomon coded single-stranded representation learning (RSRL), a novel end-to-end model for learning representations for lossless DNA data storage. In contrast to existing learning-based methods, RSRL is inspired by both error-correction codec and structural biology. Specific
Representation intervention has emerged as a promising paradigm for aligning large language models toward desired behaviors without modifying model weights. Existing methods typically apply a fixed intervention uniformly across all inputs. However, we find that the appropriate intervention direction…
Modern video-text retrieval (VTR) models excel on in-distribution benchmarks but are highly vulnerable to real-world *query shifts*, where the distribution of query data deviates from the training domain, leading to a sharp performance drop. Existing image-focused robustness solutions are inadequate…
Machine unlearning aims to erase requested data from trained models without full retraining. For Reasoning Multimodal Large Language Models (RMLLMs), this is uniquely challenging: intermediate chain-of-thought steps can still leak sensitive information even when final answers are forgotten, and over
Visual Language Models (VLMs) like GPT-4V have broadened the scope of LLM applications, yet they face significant challenges in accurately processing visual details, particularly in scientific diagrams. This paper explores the necessity of meticulous visual detail collection and region decompositio…
Despite recent advances, Text-to-video retrieval (TVR) is still hindered by multiple inherent uncertainties, such as ambiguous textual queries, indistinct text-video mappings, and low-quality video frames. Although interactive systems have emerged to address these challenges by refining user intent…
Document-level Relation Extraction (DocRE) aims to identify relationships between entity pairs within a document. However, most existing methods assume a uniform label distribution, resulting in suboptimal performance on real-world, imbalanced datasets. To tackle this challenge, we propose a novel d…
Existing Moment retrieval (MR) methods focus on Single-Moment Retrieval (SMR). However, one query can correspond to multiple relevant moments in real-world applications. This makes the existing datasets and methods insufficient for video temporal grounding. By revisiting the gap between current MR…
The generation of logically coherent dialogues by humans relies on underlying cognitive abilities. Based on this, we redefine the dialogue coherence evaluation process, combining cognitive judgment with the basic text to achieve a more human-like evaluation. We propose a novel dialogue evaluation fr…
Understanding complex events from different modalities, associating to external knowledge and generating response in a clear point of view are still unexplored in today’s multi-modal dialogue research. The great challenges include 1) lack of event-based multi-modal dialogue dataset; 2) understanding…
Knowledge graph completion (KGC) aims at inferring missing links between two entities. Most previous models focus on learning representations for entities and relations via graph neural networks. In this formalism, representations heavily rely on structural information. However, it is common for Kno…
Document-level relation extraction (DocRE) is a more challenging task for which multi-label and multi-entity problems need to be resolved effectively than its sentence-level counterpart. It aims at extracting relationships between two entities at once while taking into account significant cross-sent…
Locating the 6DoF pose of a camera in a known scene graph is a fundamental problem of SLAM. Hierarchical relocalization methods, which retrieve images first and match feature points later, have been widely studied by scholars for their high accuracy. In this paper, based on hierarchical relocalizati
Current state-of-the-art semantic segmentation methods usually require high computational resources for accurate segmentation. Knowledge distillation has been one promising way to achieve a good trade-off between accuracy and efficiency. However, current distillation methods focus on transferring th…
Recent progress on parse tree encoder for sentence representation learning is notable. However, these works mainly en-code tree structures recursively, which is not conducive to parallelization. On the other hand, these works rarely take into account the labels of arcs in dependency trees. To addres…
Recently, with the rise of high dynamic range (HDR) display devices, there is a great demand to transfer traditional low dynamic range (LDR) images into HDR versions. The key to success is how to solve the many-to-many mapping problem. However, the existing approaches either do not consider constrai…