相关论文: Consensus-based Sequence Training for Video Captio…

Generating natural and accurate descriptions in image cap-tioning has always been a challenge. In this paper, we pro-pose a novel recall mechanism to imitate the way human con-duct captioning. There are three parts in our recall mecha-nism…

Vision language (VL) models like CLIP are robust to natural distribution shifts, in part because CLIP learns on unstructured data using a technique called caption supervision; the model inteprets image-linked texts as ground-truth labels.…

Sign Language Representation Learning (SLRL) is crucial for a range of sign language-related downstream tasks such as Sign Language Translation (SLT) and Sign Language Retrieval (SLRet). Recently, many gloss-based and gloss-free SLRL…

Reinforcement Learning with Verifiable Rewards ( RLVR ) has emerged as a transformative paradigm for enhancing the reasoning capabilities of Large Language Models ( LLMs), yet its potential in 3D scene understanding remains under-explored.…

Recent Visual Question Answering (VQA) models have shown impressive performance on the VQA benchmark but remain sensitive to small linguistic variations in input questions. Existing approaches address this by augmenting the dataset with…

The core objective of image captioning is to achieve lossless semantic compression from visual signals into textual modalities. However, the reliance on manually curated reference texts for evaluation essentially forces models to mimic…

Sequence-level learning objective has been widely used in captioning tasks to achieve the state-of-the-art performance for many models. In this objective, the model is trained by the reward on the quality of its generated captions…

Generating textual descriptions for images has been an attractive problem for the computer vision and natural language processing researchers in recent years. Dozens of models based on deep learning have been proposed to solve this problem.…

Reinforcement Learning (RL) benefits Large Language Models (LLMs) for complex reasoning. Inspired by this, we explore integrating spatio-temporal specific rewards into Multimodal Large Language Models (MLLMs) to address the unique…

Conversational speech recognition is regarded as a challenging task due to its free-style speaking and long-term contextual dependencies. Prior work has explored the modeling of long-range context through RNNLM rescoring with improved…

Existing dense or paragraph video captioning approaches rely on holistic representations of videos, possibly coupled with learned object/action representations, to condition hierarchical language decoders. However, they fundamentally lack…

The explosive growth of video streaming presents challenges in achieving high accuracy and low training costs for video-language retrieval. However, existing methods rely on large-scale pre-training to improve video retrieval performance,…

This paper describes our winning entry in the ImageCLEF 2015 image sentence generation task. We improve Google's CNN-LSTM model by introducing concept-based sentence reranking, a data-driven approach which exploits the large amounts of…

Recent multi-modal large language models (MLLMs) often struggle to generate personalized image captions, even when trained on high-quality captions. In this work, we observe that such limitations persist in existing post-training-based MLLM…

Multimodal Large Language Models (MLLMs) perform well in single-image visual grounding but struggle with real-world tasks that demand cross-image reasoning and multi-modal instructions. To address this, we adopt a reinforcement learning…

Standard attention-based transformers are known to exhibit instability under learning rate overspecification during training, particularly at high learning rates. While various methods have been proposed to improve resilience to such…

Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large language models (MLLMs) has demonstrated strong capabilities in…

Measuring alignment between language and vision is a fundamental challenge, especially as multimodal data becomes increasingly detailed and complex. Existing methods often rely on collecting human or AI preferences, which can be costly and…

Improving sample efficiency is a key research problem in reinforcement learning (RL), and CURL, which uses contrastive learning to extract high-level features from raw pixels of individual video frames, is an efficient…

This paper addresses the temporal sentence grounding (TSG). Although existing methods have made decent achievements in this task, they not only severely rely on abundant video-query paired data for training, but also easily fail into the…