Related papers: MVP: Motion Vector Propagation for Zero-Shot Video…

Open-Vocabulary Video Instance Segmentation (VIS) is attracting increasing attention due to its ability to segment and track arbitrary objects. However, the recent Open-Vocabulary VIS attempts obtained unsatisfactory results, especially in…

Prompt-OVD is an efficient and effective framework for open-vocabulary object detection that utilizes class embeddings from CLIP as prompts, guiding the Transformer decoder to detect objects in both base and novel classes. Additionally, our…

Autonomous navigation emerges from both motion and local visual perception in real-world environments. However, most successful robotic motion estimation methods (e.g. VO, SLAM, SfM) and vision systems (e.g. CNN, visual place…

We propose a lightweight compressed-domain tracking model that operates directly on video streams, without requiring full RGB video decoding. Using motion vectors and transform coefficients from compressed data, our deep model propagates…

Video Semantic Segmentation (VSS) involves assigning a semantic label to each pixel in a video sequence. Prior work in this field has demonstrated promising results by extending image semantic segmentation models to exploit temporal…

GUI grounding, which translates natural language instructions into precise pixel coordinates, is essential for developing practical GUI agents. However, we observe that existing grounding models exhibit significant coordinate prediction…

Image-based visual-language (I-VL) pre-training has shown great success for learning joint visual-textual representations from large-scale web data, revealing remarkable ability for zero-shot generalisation. This paper presents a simple but…

Vision Transformer (ViT) models have recently emerged as powerful and versatile models for various visual tasks. Recently, a work called PMF has achieved promising results in few-shot image classification by utilizing pre-trained vision…

Open-vocabulary (OV) 3D object detection is an emerging field, yet its exploration through image-based methods remains limited compared to 3D point cloud-based methods. We introduce OpenM3D, a novel open-vocabulary multi-view indoor 3D…

Utilizing vision and language models (VLMs) pre-trained on large-scale image-text pairs is becoming a promising paradigm for open-vocabulary visual recognition. In this work, we extend this paradigm by leveraging motion and audio that…

We propose a Leaked Motion Video Predictor (LMVP) to predict future frames by capturing the spatial and temporal dependencies from given inputs. The motion is modeled by a newly proposed component, motion guider, which plays the role of…

We propose an end-to-end learned video compression scheme for low-latency scenarios. Previous methods are limited in using the previous one frame as reference. Our method introduces the usage of the previous multiple frames as references.…

This paper presents DetCLIPv2, an efficient and scalable training framework that incorporates large-scale image-text pairs to achieve open-vocabulary object detection (OVD). Unlike previous OVD frameworks that typically rely on a…

Reinforcement learning based post-training paradigms for Video Large Language Models (VideoLLMs) have achieved significant success by optimizing for visual-semantic tasks such as captioning or VideoQA. However, while these approaches…

Open-vocabulary object detection enables models to localize and recognize objects beyond a predefined set of categories and is expected to achieve recognition capabilities comparable to human performance. In this study, we aim to evaluate…

Object tracking is central to robot perception and scene understanding. Tracking-by-detection has long been a dominant paradigm for object tracking of specific object categories. Recently, large-scale pre-trained models have shown promising…

Detecting anomalies within point clouds is crucial for various industrial applications, but traditional unsupervised methods face challenges due to data acquisition costs, early-stage production constraints, and limited generalization…

Prompt ensembling of Large Language Model (LLM) generated category-specific prompts has emerged as an effective method to enhance zero-shot recognition ability of Vision-Language Models (VLMs). To obtain these category-specific prompts, the…

The adaptation of large-scale vision-language models (VLMs) to downstream tasks with limited labeled data remains a significant challenge. While parameter-efficient prompt learning methods offer a promising path, they often suffer from…

We introduce a one-shot learning approach for video object tracking. The proposed algorithm requires seeing the object to be tracked only once, and employs an external memory to store and remember the evolving features of the foreground…