Jingyu Li

Kaiming Kuang, Li Zhang, Jingyu Li et al.

3D reconstruction of pulmonary segments plays an important role in surgical treatment planning of lung cancer, which facilitates preservation of pulmonary function and helps ensure low recurrence rates. However, automatic reconstruction of pulmonary segments remains unexplored in the era of deep learning. In this paper, we investigate what makes for automatic reconstruction of pulmonary segments. First and foremost, we formulate, clinically and geometrically, the anatomical definitions of pulmonary segments, and propose evaluation metrics adhering to these definitions. Second, we propose ImPulSe (Implicit Pulmonary Segment), a deep implicit surface model designed for pulmonary segment reconstruction. The automatic reconstruction of pulmonary segments by ImPulSe is accurate in metrics and visually appealing. Compared with canonical segmentation methods, ImPulSe outputs continuous predictions of arbitrary resolutions with higher training efficiency and fewer parameters. Lastly, we experiment with different network inputs to analyze what matters in the task of pulmonary segment reconstruction. Our code is available at https://github.com/M3DV/ImPulSe.

Cheng Ye, Weidong Chen, Jingyu Li et al.

Emotional Video Captioning is an emerging task that aims to describe factual content with the intrinsic emotions expressed in videos. The essential of the EVC task is to effectively perceive subtle and ambiguous visual emotional cues during the caption generation, which is neglected by the traditional video captioning. Existing emotional video captioning methods perceive global visual emotional cues at first, and then combine them with the video features to guide the emotional caption generation, which neglects two characteristics of the EVC task. Firstly, their methods neglect the dynamic subtle changes in the intrinsic emotions of the video, which makes it difficult to meet the needs of common scenes with diverse and changeable emotions. Secondly, as their methods incorporate emotional cues into each step, the guidance role of emotion is overemphasized, which makes factual content more or less ignored during generation. To this end, we propose a dual-path collaborative generation network, which dynamically perceives visual emotional cues evolutions while generating emotional captions by collaborative learning. Specifically, in the dynamic emotion perception path, we propose a dynamic emotion evolution module, which first aggregates visual features and historical caption features to summarize the global visual emotional cues, and then dynamically selects emotional cues required to be re-composed at each stage. Besides, in the adaptive caption generation path, to balance the description of factual content and emotional cues, we propose an emotion adaptive decoder. Thus, our methods can generate emotion-related words at the necessary time step, and our caption generation balances the guidance of factual content and emotional cues well. Extensive experiments on three challenging datasets demonstrate the superiority of our approach and each proposed module.

Tianheng Qiu, Jingchun Gao, Jingyu Li et al.

Intent-oriented controlled video captioning aims to generate targeted descriptions for specific targets in a video based on customized user intent. Current Large Visual Language Models (LVLMs) have gained strong instruction following and visual comprehension capabilities. Although the LVLMs demonstrated proficiency in spatial and temporal understanding respectively, it was not able to perform fine-grained spatial control in time sequences in direct response to instructions. This substantial spatio-temporal gap complicates efforts to achieve fine-grained intention-oriented control in video. Towards this end, we propose a novel IntentVCNet that unifies the temporal and spatial understanding knowledge inherent in LVLMs to bridge the spatio-temporal gap from both prompting and model perspectives. Specifically, we first propose a prompt combination strategy designed to enable LLM to model the implicit relationship between prompts that characterize user intent and video sequences. We then propose a parameter efficient box adapter that augments the object semantic information in the global visual context so that the visual token has a priori information about the user intent. The final experiment proves that the combination of the two strategies can further enhance the LVLM's ability to model spatial details in video sequences, and facilitate the LVLMs to accurately generate controlled intent-oriented captions. Our proposed method achieved state-of-the-art results in several open source LVLMs and was the runner-up in the IntentVC challenge. Our code is available on https://github.com/thqiu0419/IntentVCNet.

Xiongtao Zhou, Jie He, Lanyu Chen et al.

Multimodal Chain of Thought (MCoT) is a popular prompting strategy for improving the performance of multimodal large language models (MLLMs) across a range of complex reasoning tasks. Despite its popularity, there is a notable absence of automated methods for evaluating the quality of reasoning steps in MCoT. To address this gap, we propose Multimodal Chain-of-Thought Evaluation (MiCEval), a framework designed to assess the correctness of reasoning chains by evaluating the quality of both the description and each reasoning step. The evaluation of the description component focuses on the accuracy of the image descriptions, while the reasoning step evaluates the quality of each step as it is conditionally generated based on the preceding steps. MiCEval is built upon a fine-grained dataset with annotations that rate each step according to correctness, relevance, and informativeness. Extensive experiments on four state-of-the-art MLLMs show that step-wise evaluations using MiCEval align more closely with human judgments compared to existing methods based on cosine similarity or fine-tuning approaches. MiCEval datasets and code can be found in https://github.com/alenai97/MiCEval.

Jialong Zuo, Guangyan Zhang, Minghui Fang et al.

Discrete speech representation learning has recently attracted increasing interest in both acoustic and semantic modeling. Existing approaches typically encode 16 kHz waveforms into discrete tokens at a rate of 25 or 50 tokens per second. However, given that speech generally conveys only 2 to 5 words per second, such fine-grained tokenization introduces redundancy and hinders efficiency in downstream training and inference. Moreover, semantic speech representations at this frequency primarily capture phonetic-level information, while semantic understanding may not require such detailed token-level resolution. To address these limitations, we propose an entropy-based dynamic aggregation framework for learning compressed semantic speech representations. A speech language model is first pre-trained via next-token prediction on large-scale unlabeled data to capture frequent token patterns. Predictive entropy is then used to adaptively determine aggregation boundaries, followed by a cross-attention module that fuses information within each segment. By adjusting the entropy threshold, the granularity and compression ratio of the representations can be flexibly controlled. Experiments on ASR, speech-to-text translation, and voice conversion tasks demonstrate that the compressed representations perform on par with or better than dense token sequences, demonstrating the effectiveness of the proposed approach.