Related papers: Pixel-level Scene Understanding in One Token: Visu…
We introduce CompTok, a training framework for learning visual tokenizers whose tokens are enhanced for compositionality. CompTok uses a token-conditioned diffusion decoder. By employing an InfoGAN-style objective, where we train a…
This dissertation addresses visual scene understanding and enhances segmentation performance and generalization, training efficiency of networks, and holistic understanding. First, we investigate semantic segmentation in the context of…
This work explores the use of spatial context as a source of free and plentiful supervisory signal for training a rich visual representation. Given only a large, unlabeled image collection, we extract random pairs of patches from each image…
Building a unified visual tokenizer is essential for bridging the gap between visual understanding and generation. Yet existing approaches struggle with the inherent conflict between these tasks, as a single token space is forced to support…
Referring image segmentation is a challenging task that involves generating pixel-wise segmentation masks based on natural language descriptions. The complexity of this task increases with the intricacy of the sentences provided. Existing…
Convolutional neural networks (CNN) are known to learn an image representation that captures concepts relevant to the task, but do so in an implicit way that hampers model interpretability. However, one could argue that such a…
This paper presents the Visual Place Cell Encoding (VPCE) model, a biologically inspired computational framework for simulating place cell-like activation using visual input. Drawing on evidence that visual landmarks play a central role in…
Reading text in real-world scenarios often requires understanding the context surrounding it, especially when dealing with poor-quality text. However, current scene text recognizers are unaware of the bigger picture as they operate on…
Self-supervised learning (SSL) has made rapid progress, yet learned features often over-rely on contextual shortcuts-background textures and co-occurrence statistics. While video provides rich temporal variation, dense in-the-wild streams…
Existing Scene Text Recognition (STR) methods typically use a language model to optimize the joint probability of the 1D character sequence predicted by a visual recognition (VR) model, which ignore the 2D spatial context of visual…
Scene recognition is currently one of the top-challenging research fields in computer vision. This may be due to the ambiguity between classes: images of several scene classes may share similar objects, which causes confusion among them.…
Situation Recognition is the task of generating a structured summary of what is happening in an image using an activity verb and the semantic roles played by actors and objects. In this task, the same activity verb can describe a diverse…
Visual grounding (VG) aims to establish fine-grained alignment between vision and language. Ideally, it can be a testbed for vision-and-language models to evaluate their understanding of the images and texts and their reasoning abilities…
Scene text recognition is a challenging task due to diverse variations of text instances in natural scene images. Conventional methods based on CNN-RNN-CTC or encoder-decoder with attention mechanism may not fully investigate stable and…
Visual localization remains challenging in dynamic environments where fluctuating lighting, adverse weather, and moving objects disrupt appearance cues. Despite advances in feature representation, current absolute pose regression methods…
To endow machines with the ability to perceive the real-world in a three dimensional representation as we do as humans is a fundamental and long-standing topic in Artificial Intelligence. Given different types of visual inputs such as…
Performing data augmentation for learning deep neural networks is known to be important for training visual recognition systems. By artificially increasing the number of training examples, it helps reducing overfitting and improves…
The ability to recognize objects is an essential skill for a robotic system acting in human-populated environments. Despite decades of effort from the robotic and vision research communities, robots are still missing good visual perceptual…
Historically, feature-based approaches have been used extensively for camera-based robot perception tasks such as localization, mapping, tracking, and others. Several of these approaches also combine other sensors (inertial sensing, for…
We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA.…