Related papers: Unifying Heterogeneous Multi-Modal Remote Sensing …

The multimodal fusion of images and scene captions has been extensively explored and applied in various fields. However, when dealing with complex remote sensing (RS) scenes, existing studies have predominantly concentrated on architectural…

Large vision-language models (LVLMs) often hallucinate objects that are not present in the input image, largely because visual grounding weakens as decoding progresses. Existing inference-time mitigation methods modify logits or hidden…

Multimodal embedding models, built upon causal Vision Language Models (VLMs), have shown promise in various tasks. However, current approaches face three key limitations: the use of causal attention in VLM backbones is suboptimal for…

Accurate and robust multimodal multi-task perception is crucial for modern autonomous driving systems. However, current multimodal perception research follows independent paradigms designed for specific perception tasks, leading to a lack…

Remote sensing scene classification (RSSC) is a critical task with diverse applications in land use and resource management. While unimodal image-based approaches show promise, they often struggle with limitations such as high intra-class…

Semi-supervised learning (SSL) has become a promising direction for medical image segmentation, enabling models to learn from limited labeled data alongside abundant unlabeled samples. However, existing SSL approaches for multi-modal…

Multimodal learning aims to imitate human beings to acquire complementary information from multiple modalities for various downstream tasks. However, traditional aggregation-based multimodal fusion methods ignore the inter-modality…

Self-supervised pre-training using unlabeled data is widely used in automatic speech recognition. In this paper, we propose a new self-supervised pre-training approach to dealing with heterogeneous data. Instead of mixing all the data and…

Vision-and-Language navigation (VLN) requires an agent to navigate in unseen environment by following natural language instruction. For task completion, the agent needs to align and integrate various navigation modalities, including…

Multimodal semantic communication has great potential to enhance downstream task performance by integrating complementary information across modalities. This paper introduces ProMSC-MIS, a novel Prompt-based Multimodal Semantic…

Large Vision Language Models (LVLMs) have demonstrated impressive zero-shot capabilities in various vision-language dialogue scenarios. However, the absence of fine-grained visual object detection hinders the model from understanding the…

Multimodal object detection offers a promising prospect to facilitate robust detection in various visual conditions. However, existing two-stream backbone networks are challenged by complex fusion and substantial parameter increments. This…

Image-based shape retrieval (IBSR) aims to retrieve 3D models from a database given a query image, hence addressing a classical task in computer vision, computer graphics, and robotics. Recent approaches typically rely on bridging the…

Multimodal pretraining is an effective strategy for the trinity of goals of representation learning in autonomous robots: 1) extracting both local and global task progressions; 2) enforcing temporal consistency of visual representation; 3)…

Large vision-language models (LVLMs) have achieved impressive results in various vision-language tasks. However, despite showing promising performance, LVLMs suffer from hallucinations caused by language bias, leading to diminished focus on…

Fine-tuning large language models (LLMs) with low-rank adaptation (LoRA) is a cost-effective way to incorporate information from a specific dataset. However, when a problem requires incorporating information from multiple datasets - as in…

Even modern AI models often remain vulnerable to multimodal queries in which harmful intent is embedded in images. A widely used approach for safety alignment is training with extensive multimodal safety datasets, but the costs of data…

The goal of Multilingual Visual Answer Localization (MVAL) is to locate a video segment that answers a given multilingual question. Existing methods either focus solely on visual modality or integrate visual and subtitle modalities.…

Adapting large-scale Vision-Language Models (VLMs) like CLIP to downstream tasks often suffers from a "one-size-fits-all" architectural approach, where visual and textual tokens are processed uniformly by wide, generic adapters. We argue…

Multi-Modal LLMs (MLLMs) demonstrate strong visual grounding capabilities on popular object detection benchmarks like OdinW-13 and RefCOCO. However, state-of-the-art models still struggle to generalize to out-of-distribution classes, tasks…