相关论文: Pseudo-Q: Generating Pseudo Language Queries for V…

Open-vocabulary instance segmentation aims at segmenting novel classes without mask annotations. It is an important step toward reducing laborious human supervision. Most existing works first pretrain a model on captioned images covering…

Recent advances in vision-language models have shown notable generalization in broad tasks through visual instruction tuning. However, bridging the gap between the pre-trained vision encoder and the large language models (LLMs) becomes the…

We propose a new task and model for dense video object captioning -- detecting, tracking and captioning trajectories of objects in a video. This task unifies spatial and temporal localization in video, whilst also requiring fine-grained…

Language is highly structured, with syntactic and semantic structures, to some extent, agreed upon by speakers of the same language. With implicit or explicit awareness of such structures, humans can learn and use language efficiently and…

3D visual grounding is a critical skill for household robots, enabling them to navigate, manipulate objects, and answer questions based on their environment. While existing approaches often rely on extensive labeled data or exhibit…

Visual question answering is the task of answering questions about images. We introduce the VizWiz-VQA-Grounding dataset, the first dataset that visually grounds answers to visual questions asked by people with visual impairments. We…

We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation…

Transformers for visual-language representation learning have been getting a lot of interest and shown tremendous performance on visual question answering (VQA) and grounding. But most systems that show good performance of those tasks still…

Visual question answering (VQA) refers to the problem where, given an image and a natural language question about the image, a correct natural language answer has to be generated. A VQA model has to demonstrate both the visual understanding…

In this work, we tackle the egocentric visual query localization (VQL), where a model should localize the query object in a long-form egocentric video. Frequent and abrupt viewpoint changes in egocentric videos cause significant object…

We introduce the novel problem of localizing all the instances of an object (seen or unseen during training) in a natural image via sketch query. We refer to this problem as sketch-guided object localization. This problem is distinctively…

Visual Question Answering (VQA) is a novel problem domain where multi-modal inputs must be processed in order to solve the task given in the form of a natural language. As the solutions inherently require to combine visual and natural…

Visual grounding is a common vision task that involves grounding descriptive sentences to the corresponding regions of an image. Most existing methods use independent image-text encoding and apply complex hand-crafted modules or…

In the realm of cross-modal retrieval, seamlessly integrating diverse modalities within multimedia remains a formidable challenge, especially given the complexities introduced by noisy correspondence learning (NCL). Such noise often stems…

Open-vocabulary detection aims to detect objects from novel categories beyond the base categories on which the detector is trained. However, existing open-vocabulary detectors trained on base category data tend to assign higher confidence…

We study visually grounded VideoQA in response to the emerging trends of utilizing pretraining techniques for video-language understanding. Specifically, by forcing vision-language models (VLMs) to answer questions and simultaneously…

We present RELOCATE, a simple training-free baseline designed to perform the challenging task of visual query localization in long videos. To eliminate the need for task-specific training and efficiently handle long videos, RELOCATE…

Recently, Visual Question Answering (VQA) has emerged as one of the most significant tasks in multimodal learning as it requires understanding both visual and textual modalities. Existing methods mainly rely on extracting image and question…

Recently introduced self-supervised methods for image representation learning provide on par or superior results to their fully supervised competitors, yet the corresponding efforts to explain the self-supervised approaches lag behind.…

Recently, Vision Language Models (VLMs) have increasingly emphasized document visual grounding to achieve better human-computer interaction, accessibility, and detailed understanding. However, its application to visualizations such as…