Related papers: A 2D Semantic-Aware Position Encoding for Vision T…

This paper presents a novel semantic scene change detection scheme with only weak supervision. A straightforward approach for this task is to train a semantic change detection network directly from a large-scale dataset in an end-to-end…

Visual-Semantic Embedding (VSE) aims to learn an embedding space where related visual and semantic instances are close to each other. Recent VSE models tend to design complex structures to pool visual and semantic features into fixed-length…

Embedding methods transform the knowledge graph into a continuous, low-dimensional space, facilitating inference and completion tasks. Existing methods are mainly divided into two types: translational distance models and semantic matching…

Semantic correspondence is the problem of establishing correspondences across images depicting different instances of the same object or scene class. One of recent approaches to this problem is to estimate parameters of a global…

Current vision systems typically assign fixed-length representations to images, regardless of the information content. This contrasts with human intelligence - and even large language models - which allocate varying representational…

A large body of recent work targets semantically conditioned image generation. Most such methods focus on the narrower task of pose transfer and ignore the more challenging task of subject transfer that consists in not only transferring the…

To solve video-and-language grounding tasks, the key is for the network to understand the connection between the two modalities. For a pair of video and language description, their semantic relation is reflected by their encodings'…

In this work, we propose a novel paradigm to encode the position of targets for target tracking in videos using transformers. The proposed paradigm, Dense Spatio-Temporal (DST) position encoding, encodes spatio-temporal position information…

Although Vision Transformers (ViTs) have recently advanced computer vision tasks significantly, an important real-world problem was overlooked: adapting to variable input resolutions. Typically, images are resized to a fixed resolution,…

Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image. One of the key challenges behind this task is leveraging the referring…

Unsupervised visual defect detection is critical in industrial applications, requiring a representation space that captures normal data features while detecting deviations. Achieving a balance between expressiveness and compactness is…

Enabling mobile robots for solving challenging and diverse shape, texture, and motion related tasks with high fidelity vision requires the integration of novel multimodal imaging sensors and advanced fusion techniques. However, it is…

Jointing visual-semantic embeddings (VSE) have become a research hotpot for the task of image annotation, which suffers from the issue of semantic gap, i.e., the gap between images' visual features (low-level) and labels' semantic features…

Remote sensing image change captioning (RSICC) aims to articulate the changes in objects of interest within bi-temporal remote sensing images using natural language. Given the limitations of current RSICC methods in expressing general…

In this work we present a novel approach to joint semantic localisation and scene understanding. Our work is motivated by the need for localisation algorithms which not only predict 6-DoF camera pose but also simultaneously recognise…

Visual Place Recognition (VPR) in long-term deployment requires reasoning beyond pixel similarity: systems must make transparent, interpretable decisions that remain robust under lighting, weather and seasonal change. We present Text2Graph…

Scene-agnostic visual inpainting remains very challenging despite progress in patch-based methods. Recently, Pathak et al. 2016 have introduced convolutional "context encoders" (CEs) for unsupervised feature learning through image…

Rotary Positional Encoding (RoPE) is widely used in modern large language models. However, when sequences are extended beyond the range seen during training, rotary phases can enter out-of-distribution regimes, leading to spurious…

Visual localization is a fundamental task for various applications including autonomous driving and robotics. Prior methods focus on extracting large amounts of often redundant locally reliable features, resulting in limited efficiency and…

Visual data compression is shifting from human-centered reconstruction to machine-oriented representation coding. In this setting, an image is often mapped to a compact semantic embedding, which is then compressed and transmitted for…