Related papers: Beyond Detection: A Structure-Aware Framework for …
Scene text image contains two levels of contents: visual texture and semantic information. Although the previous scene text recognition methods have made great progress over the past few years, the research on mining semantic information to…
Online contextual reasoning and association across consecutive video frames are critical to perceive instances in visual tracking. However, most current top-performing trackers persistently lean on sparse temporal relationships between…
Creating machines capable of understanding the world in 3D is essential in assisting designers that build and edit 3D environments and robots navigating and interacting within a three-dimensional space. Inspired by advances in language and…
Style-conditioned scene text generation faces unique challenges in extracting precise text styles from complex backgrounds and maintaining fine-grained style consistency across characters, especially for multilingual scripts. We propose…
In this paper, we introduce a new sequence-to-sequence learning framework for RGB-based and multi-modal object tracking. First, we present SeqTrack for RGB-based tracking. It casts visual tracking as a sequence generation task, forecasting…
We introduce a generalized framework for Scene Change Detection (SCD) that addresses the core ambiguity of distinguishing "relevant" from "nuisance" changes, enabling effective joint training of a single model across diverse domains and…
Dominant scene text recognition models commonly contain two building blocks, a visual model for feature extraction and a sequence model for text transcription. This hybrid architecture, although accurate, is complex and less efficient. In…
Perceiving the world in terms of objects and tracking them through time is a crucial prerequisite for reasoning and scene understanding. Recently, several methods have been proposed for unsupervised learning of object-centric…
This paper focuses on the problem of script identification in unconstrained scenarios. Script identification is an important prerequisite to recognition, and an indispensable condition for automatic text understanding systems designed for…
Scene text erasing, which replaces text regions with reasonable content in natural images, has drawn significant attention in the computer vision community in recent years. There are two potential subtasks in scene text erasing: text…
Recently, segmentation-based methods are quite popular in scene text detection, which mainly contain two steps: text kernel segmentation and expansion. However, the segmentation process only considers each pixel independently, and the…
Drone-based crowd tracking faces difficulties in accurately identifying and monitoring objects from an aerial perspective, largely due to their small size and close proximity to each other, which complicates both localization and tracking.…
Recently, scene text recognition methods based on deep learning have sprung up in computer vision area. The existing methods achieved great performances, but the recognition of irregular text is still challenging due to the various shapes…
Automated text detection is a difficult computer vision task. In order to accurately detect and identity text in an image or video, two major problems must be addressed. The primary problem is implementing a robust and reliable method for…
The tracking-by-detection framework requires a set of positive and negative training samples to learn robust tracking models for precise localization of target objects. However, existing tracking models mostly treat different samples…
Recently, video text detection, tracking, and recognition in natural scenes are becoming very popular in the computer vision community. However, most existing algorithms and benchmarks focus on common text cases (e.g., normal size, density)…
The ability to detect and track objects in the visual world is a crucial skill for any intelligent agent, as it is a necessary precursor to any object-level reasoning process. Moreover, it is important that agents learn to track objects…
Self-supervised learning has drawn attention through its effectiveness in learning in-domain representations with no ground-truth annotations; in particular, it is shown that properly designed pretext tasks (e.g., contrastive prediction…
In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or…
In this paper, we aim to model 3D scene geometry, appearance, and physical information just from dynamic multi-view videos in the absence of any human labels. By leveraging physics-informed losses as soft constraints or integrating simple…