Dense video captioning aims to localize events within input videos and generate concise descriptive texts for each event. Advanced end-to-end methods require both tasks to share the same intermediate features that serve as event queries, thereby enabling the mutual promotion of two tasks. However, relying on shared queries limits the model’s ability to extract task-specific information, as event semantic perception and localization demand distinct perspectives on video understanding. To address this, we propose a decomposed dense video captioning framework that derives localization and captioning queries from event queries, enabling task-specific representations while maintaining inter-task collaboration. Considering the roles of different queries, we design a contrastive semantic optimization strategy that guides localization queries to focus on event-level visual features and captioning queries to align with textual semantics. Besides, only localization information is considered in existing methods for label assignment, failing to ensure the relevance of the selected queries to descriptions. We jointly consider localization and captioning losses to achieve a semantically balanced assignment process. Extensive experiments on the YouCook2 and ActivityNet Captions datasets demonstrate that our framework achieves state-of-the-art performance.

Multimodal Sentiment Analysis (MSA) is the task of understanding human emotions by analyzing a combination of different data sources, such as text, audio, and visual inputs. Although recent advances have improved emotion modeling across modalities, existing methods still struggle with two fundamental challenges: balancing global and fine-grained sentiment contributions, and over-reliance on the text modality. To address these issues, we propose DPDF-LQ (Dual-Path Dynamic Fusion with Learnable Query), an architecture that processes inputs through two complementary paths: global and local. The global path is responsible for establishing cross-modal dependencies, while the local path captures fine-grained representations. Additionally, we introduce the key module Dynamic Global Learnable Query Attention (DGLQA) in the global path, which dynamically allocates weights to each modality to capture their relevant features and learn global representations. Extensive experiments on the CMU-MOSI and CMU-MOSEI benchmarks demonstrate that DPDF-LQ achieves state-of-the-art performance, particularly in fine-grained sentiment prediction by effectively combining global and local features. Our code will be released at https://github.com/ZhouMiaoGX/DPDF-LQ.

Lexical-level sentence simplification is essential for improving text accessibility, yet traditional methods often struggle to dynamically identify complex terms and generate contextually appropriate substitutions, resulting in limited generalization. While prompt-based approaches with large language models (LLMs) have shown strong performance and adaptability, they often lack interpretability and are prone to hallucinating. This study proposes a fine-tuning approach for mid-sized LLMs to emulate the lexical simplification pipeline. We transform complex word identification datasets into an instruction–response format to support instruction tuning. Experimental results show that our method substantially enhances complex word identification accuracy with reduced hallucinations while achieving competitive performance on lexical simplification benchmarks. Furthermore, we find that integrating fine-tuning with prompt engineering reduces dependency on manual prompt optimization, leading to a more efficient simplification framework.