Related papers: SeqTR: A Simple yet Universal Network for Visual G…

We present a new method for efficient high-quality image segmentation of objects and scenes. By analogizing classical computer graphics methods for efficient rendering with over- and undersampling challenges faced in pixel labeling tasks,…

Recently, Referring Image Segmentation (RIS) frameworks that pair the Multimodal Large Language Model (MLLM) with the Segment Anything Model (SAM) have achieved impressive results. However, adapting MLLM to segmentation is computationally…

Visual localization algorithms have achieved significant improvements in performance thanks to recent advances in camera technology and vision-based techniques. However, there remains one critical caveat: all current approaches that are…

Video Temporal Grounding (VTG) aims to identify visual frames in a video clip that match text queries. Recent studies in VTG employ cross-attention to correlate visual frames and text queries as individual token sequences. However, these…

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…

Remote sensing visual grounding (RSVG) aims to localize objects in remote sensing imagery according to natural language expressions. Previous methods typically rely on sentence-level vision-language alignment, which struggles to exploit…

Visual context provides grounding information for multimodal machine translation (MMT). However, previous MMT models and probing studies on visual features suggest that visual information is less explored in MMT as it is often redundant to…

3D visual grounding consists of identifying the instance in a 3D scene which is referred by an accompanying language description. While several architectures have been proposed within the commonly employed grounding-by-selection framework,…

Unlike Object Detection, Visual Grounding task necessitates the detection of an object described by complex free-form language. To simultaneously model such complex semantic and visual representations, recent state-of-the-art studies adopt…

Task arithmetic, representing downstream tasks through linear operations on task vectors, has emerged as a simple yet powerful paradigm for transferring knowledge across diverse settings. However, maintaining a large collection of task…

End-to-end trained Recurrent Neural Networks (RNNs) have been successfully applied to numerous problems that require processing sequences, such as image captioning, machine translation, and text recognition. However, RNNs often struggle to…

We propose a unified framework that integrates object detection (OD) and visual grounding (VG) for remote sensing (RS) imagery. To support conventional OD and establish an intuitive prior for VG task, we fine-tune an open-set object…

Goal-conditioned reinforcement learning (GCRL) allows agents to learn diverse objectives using a unified policy. The success of GCRL, however, is contingent on the choice of goal representation. In this work, we propose a mask-based goal…

Current one-stage methods for visual grounding encode the language query as one holistic sentence embedding before fusion with visual feature. Such a formulation does not treat each word of a query sentence on par when modeling language to…

In this work, we present a unified model that can handle both Keyword Spotting and Word Recognition with the same network architecture. The proposed network is comprised of a non-recurrent CTC branch and a Seq2Seq branch that is further…

In this work, we address the challenging task of referring segmentation. The query expression in referring segmentation typically indicates the target object by describing its relationship with others. Therefore, to find the target one…

3D visual grounding is the task of localizing the object in a 3D scene which is referred by a description in natural language. With a wide range of applications ranging from autonomous indoor robotics to AR/VR, the task has recently risen…

Recently, significant improvement has been made on semantic object segmentation due to the development of deep convolutional neural networks (DCNNs). Training such a DCNN usually relies on a large number of images with pixel-level…

Accurate and fast foreground object extraction is very important for object tracking and recognition in video surveillance. Although many background subtraction (BGS) methods have been proposed in the recent past, it is still regarded as a…

One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over the specific representations they have experienced. This is…