Related papers: Instance-Level Generation for Representation Learn…
The progress of composed image retrieval (CIR), a popular research direction in image retrieval, where a combined visual and textual query is used, is held back by the absence of high-quality training and evaluation data. We introduce a new…
Large Language Models (LLM) hold immense promise for real-world applications, but their generic knowledge often falls short of domain-specific needs. Fine-tuning, a common approach, can suffer from catastrophic forgetting and hinder…
Implicit Neural Representation (INR) has gained increasing popularity as a data representation method, serving as a prerequisite for innovative generation models. Unlike gradient-based methods, which exhibit lower efficiency in inference,…
Aerial scenes are more complicated in terms of object distribution and spatial arrangement than natural scenes due to the bird view, and thus remain challenging to learn discriminative scene representation. Recent solutions design…
Few-shot visual recognition refers to recognize novel visual concepts from a few labeled instances. Many few-shot visual recognition methods adopt the metric-based meta-learning paradigm by comparing the query representation with class…
Recent advances in text-to-video diffusion models have enabled the generation of high-quality videos conditioned on textual descriptions. However, most existing text-to-video models rely solely on textual conditions, lacking general…
Instance detection (InsDet) aims to localize specific object instances within a novel scene imagery based on given visual references. Technically, it requires proposal detection to identify all possible object instances, followed by…
Deep learning methods typically require vast amounts of training data to reach their full potential. While some publicly available datasets exists, domain specific data always needs to be collected and manually labeled, an expensive, time…
Despite the great success of the deep features in content-based image retrieval, the visual instance search remains challenging due to the lack of effective instance-level feature representation. Supervised or weakly supervised object…
Implicit Neural Representations (INRs) are powerful to parameterize continuous signals in computer vision. However, almost all INRs methods are limited to low-level tasks, e.g., image/video compression, super-resolution, and image…
The success of deep learning in computer vision is based on availability of large annotated datasets. To lower the need for hand labeled images, virtually rendered 3D worlds have recently gained popularity. Creating realistic 3D content is…
With the introduction of consumer light field cameras, light field imaging has recently become widespread. However, there is an inherent trade-off between the angular and spatial resolution, and thus, these cameras often sparsely sample in…
In recent years, the rise of large language models (LLMs) has made it possible to directly achieve named entity recognition (NER) without any demonstration samples or only using a few samples through in-context learning (ICL). However,…
Unpaired Image-to-image Translation is a new rising and challenging vision problem that aims to learn a mapping between unaligned image pairs in diverse domains. Recent advances in this field like MUNIT and DRIT mainly focus on…
In recent years, instance segmentation has garnered significant attention across various applications. However, training a fully-supervised instance segmentation model requires costly both instance-level and pixel-level annotations. In…
Visual object tracking performance has been dramatically improved in recent years, but some severe challenges remain open, like distractors and occlusions. We suspect the reason is that the feature representations of the tracking targets…
In-Context Learning (ICL) empowers Large Language Models (LLMs) with the ability to learn from a few examples provided in the prompt, enabling downstream generalization without the requirement for gradient updates. Despite encouragingly…
We introduce a general framework for visual forecasting, which directly imitates visual sequences without additional supervision. As a result, our model can be applied at several semantic levels and does not require any domain knowledge or…
Training an object detector on a data-rich domain and applying it to a data-poor one with limited performance drop is highly attractive in industry, because it saves huge annotation cost. Recent research on unsupervised domain adaptive…
A major impediment in rapidly deploying object detection models for instance detection is the lack of large annotated datasets. For example, finding a large labeled dataset containing instances in a particular kitchen is unlikely. Each new…