Related papers: Multi-Label Meta Weighting for Long-Tailed Dynamic…
In this work, we seek new insights into the underlying challenges of the Scene Graph Generation (SGG) task. Quantitative and qualitative analysis of the Visual Genome dataset implies -- 1) Ambiguity: even if inter-object relationship…
Current fully-supervised video datasets consist of only a few hundred thousand videos and fewer than a thousand domain-specific labels. This hinders the progress towards advanced video architectures. This paper presents an in-depth study of…
The performance of current Scene Graph Generation (SGG) models is severely hampered by hard-to-distinguish predicates, e.g., woman-on/standing on/walking on-beach. As general SGG models tend to predict head predicates and re-balancing…
Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between labels and discovering the locations of discriminative…
Scene graph generation (SGG) is a sophisticated task that suffers from both complex visual features and dataset long-tail problem. Recently, various unbiased strategies have been proposed by designing novel loss functions and data balancing…
Given the vast amounts of video available online, and recent breakthroughs in object detection with static images, object detection in video offers a promising new frontier. However, motion blur and compression artifacts cause substantial…
Deep learning enables impressive performance in image recognition using large-scale artificially-balanced datasets. However, real-world datasets exhibit highly class-imbalanced distributions, yielding two main challenges: relative imbalance…
Optimal viewpoint prediction is an essential task in many computer graphics applications. Unfortunately, common viewpoint qualities suffer from two major drawbacks: dependency on clean surface meshes, which are not always available, and the…
Object detection has been widely explored for class-balanced datasets such as COCO. However, real-world scenarios introduce the challenge of long-tailed distributions, where numerous categories contain only a few instances. This inherent…
Although contrastive learning methods have shown prevailing performance on a variety of representation learning tasks, they encounter difficulty when the training dataset is long-tailed. Many researchers have combined contrastive learning…
We propose a weakly-supervised approach for conditional image generation of complex scenes where a user has fine control over objects appearing in the scene. We exploit sparse semantic maps to control object shapes and classes, as well as…
Video understanding has attracted much research attention especially since the recent availability of large-scale video benchmarks. In this paper, we address the problem of multi-label video classification. We first observe that there…
Motivation: Despite recent advancements in semantic representation driven by pre-trained and large-scale language models, addressing long tail challenges in multi-label text classification remains a significant issue. Long tail challenges…
Recently, large-scale visual language pre-trained (VLP) models have demonstrated impressive performance across various downstream tasks. Motivated by these advancements, pioneering efforts have emerged in multi-label image recognition with…
In classic video action recognition, labels may not contain enough information about the diverse video appearance and dynamics, thus, existing models that are trained under the standard supervised learning paradigm may extract less…
The long-tail distribution of the visual world poses great challenges for deep learning based classification models on how to handle the class imbalance problem. Existing solutions usually involve class-balancing strategies, e.g., by loss…
Long-tailed datasets are very frequently encountered in real-world use cases where few classes or categories (known as majority or head classes) have higher number of data samples compared to the other classes (known as minority or tail…
Scene graph generation has received growing attention with the advancements in image understanding tasks such as object detection, attributes and relationship prediction,~\etc. However, existing datasets are biased in terms of object and…
Weakly-supervised video scene graph generation (WS-VSGG) aims to parse video content into structured relational triplets without bounding box annotations and with only sparse temporal labeling, significantly reducing annotation costs.…
Modern image classifiers perform well on populated classes, while degrading considerably on tail classes with only a few instances. Humans, by contrast, effortlessly handle the long-tailed recognition challenge, since they can learn the…