Related papers: Global and Local Semantic Completion Learning for …

It is widely agreed that open-vocabulary-based approaches outperform classical closed-set training solutions for recognizing unseen objects in images for semantic segmentation. Existing open-vocabulary approaches leverage vision-language…

Self-supervised Multi-modal Contrastive Learning (SMCL) remarkably advances modern Vision-Language Pre-training (VLP) models by aligning visual and linguistic modalities. Due to noises in web-harvested text-image pairs, however, scaling up…

Vision-Language Tracking aims to continuously localize objects described by a visual template and a language description. Existing methods, however, are typically limited to local search, making them prone to failures under viewpoint…

Cross-lingual in-context learning (XICL) has emerged as a transformative paradigm for leveraging large language models (LLMs) to tackle multilingual tasks, especially for low-resource languages. However, existing approaches often rely on…

Multimodal alignment between language and vision is the fundamental topic in current vision-language model research. Contrastive Captioners (CoCa), as a representative method, integrates Contrastive Language-Image Pretraining (CLIP) and…

Pre-training has been proven to be effective in boosting the performance of Isolated Sign Language Recognition (ISLR). Existing pre-training methods solely focus on the compact pose data, which eliminates background perturbation but…

Visual planning simulates how humans make decisions to achieve desired goals in the form of searching for visual causal transitions between an initial visual state and a final visual goal state. It has become increasingly important in…

Masked language modeling (MLM) is one of the key sub-tasks in vision-language pretraining. In the cross-modal setting, tokens in the sentence are masked at random, and the model predicts the masked tokens given the image and the text. In…

Despite their consistent performance improvements, cross-modal retrieval models (e.g., CLIP) show degraded performances with retrieving keys composed of fused image-text modality (e.g., Wikipedia pages with both images and text). To address…

Vision-and-language pretraining (VLP) in the medical field utilizes contrastive learning on image-text pairs to achieve effective transfer across tasks. Yet, current VLP approaches with the masked modeling strategy face two challenges when…

Is vision good enough for language? Recent advancements in multimodal models primarily stem from the powerful reasoning abilities of large language models (LLMs). However, the visual component typically depends only on the instance-level…

We propose Unicoder-VL, a universal encoder that aims to learn joint representations of vision and language in a pre-training manner. Borrow ideas from cross-lingual pre-trained models, such as XLM and Unicoder, both visual and linguistic…

Multimodal in-context learning (ICL) has emerged as a key mechanism for harnessing the capabilities of large vision-language models (LVLMs). However, its effectiveness remains highly sensitive to the quality of input ICL sequences,…

While multimodal large language models (MLLMs) have demonstrated extraordinary vision-language understanding capabilities, their abilities to solve instance-level visual-language problems beyond a single image warrant further exploration.…

Sign Language Production (SLP) aims to generate sign videos corresponding to spoken language sentences, where the conversion of sign Glosses to Poses (G2P) is the key step. Due to the cross-modal semantic gap and the lack of word-action…

Multi-label recognition with partial labels (MLR-PL), in which only some labels are known while others are unknown for each image, is a practical task in computer vision, since collecting large-scale and complete multi-label datasets is…

We present VisionLLM v2, an end-to-end generalist multimodal large model (MLLM) that unifies visual perception, understanding, and generation within a single framework. Unlike traditional MLLMs limited to text output, VisionLLM v2…

Visual Question Answering (VQA) is a multi-discipline research task. To produce the right answer, it requires an understanding of the visual content of images, the natural language questions, as well as commonsense reasoning over the…

Until recently, the success of large-scale vision-language models (VLMs) has primarily relied on billion-sample datasets, posing a significant barrier to progress. Latest works have begun to close this gap by improving supervision quality,…

Multimodal learning plays a critical role in e-commerce recommendation platforms today, enabling accurate recommendations and product understanding. However, existing vision-language models, such as CLIP, face key challenges in e-commerce…