相关论文: Reconstruction as a Bridge for Event-Based Visual …

Despite recent advancements in the Large Reconstruction Model (LRM) demonstrating impressive results, when extending its input from single image to multiple images, it exhibits inefficiencies, subpar geometric and texture quality, as well…

With the proliferation of user-generated online videos, Multimodal Sentiment Analysis (MSA) has attracted increasing attention recently. Despite significant progress, there are still two major challenges on the way towards robust MSA: 1)…

Recent advances in multimodal question answering have primarily focused on combining heterogeneous modalities or fine-tuning multimodal large language models. While these approaches have shown strong performance, they often rely on a…

Human reading comprehension often requires reasoning of event semantic relations in narratives, represented by Event-centric Question-Answering (QA). To address event-centric QA, we propose a novel QA model with contrastive learning and…

Large language models (LLMs) have achieved remarkable performance on knowledge graph question answering (KGQA) tasks by planning and interacting with knowledge graphs. However, existing methods often confuse tool utilization with knowledge…

Event cameras are innovative neuromorphic sensors that asynchronously capture the scene dynamics. Due to the event-triggering mechanism, such cameras record event streams with much shorter response latency and higher intensity sensitivity…

Event cameras are novel bio-inspired sensors that measure per-pixel brightness differences asynchronously. Recovering brightness from events is appealing since the reconstructed images inherit the high dynamic range (HDR) and high-speed…

Large language models (LLMs) have achieved state-of-the-art results in many natural language processing tasks. They have also demonstrated ability to adapt well to different tasks through zero-shot or few-shot settings. With the capability…

The advancement of Multimodal Large Language Models (MLLMs) has driven significant progress in Visual Question Answering (VQA), evolving from Single to Multi Image VQA (MVQA). However, the increased number of images in MVQA inevitably…

We present ReMatch, a framework that leverages the generative strength of MLLMs for multimodal retrieval. Previous approaches treated an MLLM as a simple encoder, ignoring its generative nature, and under-utilising its compositional…

Event cameras provide a promising sensing modality for high-speed and high-dynamic-range vision by asynchronously capturing brightness changes. A fundamental task in event-based vision is event-to-video (E2V) reconstruction, which aims to…

Video understanding with multimodal large language models (MLLMs) remains challenging due to the long token sequences of videos, which contain extensive temporal dependencies and redundant frames. Existing approaches typically treat MLLMs…

We propose a generic event camera calibration framework using image reconstruction. Instead of relying on blinking LED patterns or external screens, we show that neural-network-based image reconstruction is well suited for the task of…

Event cameras deliver visual data with high temporal resolution, low latency, and minimal redundancy, yet their asynchronous, sparse sequential nature challenges standard tensor-based machine learning (ML). While the recent…

Zero-shot visual question answering (ZS-VQA), an emerged critical research area, intends to answer visual questions without providing training samples. Existing research in ZS-VQA has proposed to leverage knowledge graphs or large language…

Zero-shot Visual Question Answering (VQA) is a prominent vision-language task that examines both the visual and textual understanding capability of systems in the absence of training data. Recently, by converting the images into captions,…

Event cameras are novel sensors that report brightness changes in the form of asynchronous "events" instead of intensity frames. They have significant advantages over conventional cameras: high temporal resolution, high dynamic range, and…

Event cameras offer significant potential for Low-light Image Enhancement (LLIE), yet existing fusion approaches are constrained by a fundamental dilemma: early fusion struggles with modality heterogeneity, while late fusion severs crucial…

While many EDA tasks already involve graph-based data, existing LLMs in EDA primarily either represent graphs as sequential text, or simply ignore graph-structured data that might be beneficial like dataflow graphs of RTL code. Recent…

In 3D Visual Question Answering (3D VQA), the scarcity of fully annotated data and limited visual content diversity hampers the generalization to novel scenes and 3D concepts (e.g., only around 800 scenes are utilized in ScanQA and SQA…