Related papers: Stitch and Tell: A Structured Multimodal Data Augm…
Transformers have gained attention in atmospheric time series forecasting (ATSF) for their ability to capture global spatial-temporal correlations. However, their complex architectures lead to excessive parameter counts and extended…
Artificial neural networks typically struggle in generalizing to out-of-context examples. One reason for this limitation is caused by having datasets that incorporate only partial information regarding the potential correlational structure…
While mel-spectrograms have been widely utilized as intermediate representations in zero-shot text-to-speech (TTS), their inherent redundancy leads to inefficiency in learning text-speech alignment. Compact VAE-based latent representations…
Scene text recognition (STR) from high-resolution (HR) images has been significantly successful, however text reading on low-resolution (LR) images is still challenging due to insufficient visual information. Therefore, recently many scene…
Dexterous manipulation requires precise geometric reasoning, yet existing visuo-tactile learning methods struggle with sub-millimeter precision tasks that are routine for traditional model-based approaches. We identify a key limitation:…
Masked video modeling, such as VideoMAE, is an effective paradigm for video self-supervised learning (SSL). However, they are primarily based on reconstructing pixel-level details on natural videos which have substantial temporal…
Video scene graph generation (VidSGG) aims to identify objects in visual scenes and infer their relationships for a given video. It requires not only a comprehensive understanding of each object scattered on the whole scene but also a deep…
We present Split-then-Merge (StM), a novel framework designed to enhance control in generative video composition and address its data scarcity problem. Unlike conventional methods relying on annotated datasets or handcrafted rules, StM…
Image-text retrieval has developed rapidly in recent years. However, it is still a challenge in remote sensing due to visual-semantic imbalance, which leads to incorrect matching of non-semantic visual and textual features. To solve this…
While recent advancements in multimodal language models have enabled image generation from expressive multi-image instructions, existing methods struggle to maintain performance under complex interleaved instructions. This limitation stems…
Thanks to the emerging of foundation models, the large language and vision models are integrated to acquire the multimodal ability of visual captioning, question answering, etc. Although existing multimodal models present impressive…
Multimodal large language models (MLLMs) have revolutionized cross-modal understanding but continue to struggle with hallucinations - fabricated content contradicting visual inputs. Existing hallucination mitigation methods either incur…
In this paper, we introduce a novel self-supervised learning (SSL) loss for image representation learning. There is a growing belief that generalization in deep neural networks is linked to their ability to discriminate object shapes. Since…
Current Large Language Models have achieved Olympiad-level logic, yet Vision-Language Models paradoxically falter on elementary spatial tasks like block counting. This capability mismatch reveals a critical ``spatial intelligence gap,''…
Though adversarial erasing has prevailed in weakly supervised semantic segmentation to help activate integral object regions, existing approaches still suffer from the dilemma of under-activation and over-expansion due to the difficulty in…
Recognizing and reasoning about occluded (partially or fully hidden) objects is vital to understanding visual scenes, as occlusions frequently occur in real-world environments and act as obstacles for spatial comprehension. To test models'…
Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a photorealistic image is synthesized from a segmentation mask. SIS has mostly been addressed as a supervised problem. However, state-of-the-art methods depend…
3D reconstruction is a useful tool for surgical planning and guidance. However, the lack of available medical data stunts research and development in this field, as supervised deep learning methods for accurate disparity estimation rely…
Extracting structured knowledge from unstructured data still faces practical limitations: entity and event extraction pipelines remain brittle, knowledge graph construction requires costly ontology engineering, and cross-domain…
Multi-modal learning adeptly integrates visual and textual data, but its application to histopathology image and text analysis remains challenging, particularly with large, high-resolution images like gigapixel Whole Slide Images (WSIs).…