Related papers: M$^5$L: Multi-Modal Multi-Margin Metric Learning f…
Crowd counting aims to estimate the number of persons in a scene. Most state-of-the-art crowd counting methods based on color images can't work well in poor illumination conditions due to invisible objects. With the widespread use of…
Achieving precise positioning of the mobile manipulator's base is essential for successful manipulation actions that follow. Most of the RGB-based navigation systems only guarantee coarse, meter-level accuracy, making them less suitable for…
Numerous studies attempt to mitigate classification bias caused by class imbalance. However, existing studies have yet to explore the collaborative optimization of imbalanced learning and model training. This constraint hinders further…
Conventional multi-label classification (MLC) methods assume that all samples are fully labeled and identically distributed. Unfortunately, this assumption is unrealistic in large-scale MLC data that has long-tailed (LT) distribution and…
Balancing performance trade-off on long-tail (LT) data distributions remains a long-standing challenge. In this paper, we posit that this dilemma stems from a phenomenon called "tail performance degradation" (the model tends to severely…
Recent works in multiple object tracking use sequence model to calculate the similarity score between the detections and the previous tracklets. However, the forced exposure to ground-truth in the training stage leads to the…
Most existing multimodal trackers adopt uniform fusion strategies, overlooking the inherent differences between modalities. Moreover, they propagate temporal information through mixed tokens, leading to entangled and less discriminative…
Deep neural networks often degrade significantly when training data suffer from class imbalance problems. Existing approaches, e.g., re-sampling and re-weighting, commonly address this issue by rearranging the label distribution of training…
RGB-T tracking leverages the complementary strengths of RGB and thermal infrared (TIR) modalities to address challenging scenarios such as low illumination and adverse weather. However, existing methods often fail to effectively integrate…
With advances in digital technology, the classification of medical images has become a crucial step for image-based clinical decision support systems. Automatic medical image classification represents a pivotal domain where the use of AI…
Large Multimodal Models (LMMs) exhibit remarkable multi-tasking ability by learning mixed instruction datasets. However, novel tasks would be encountered sequentially in dynamic world, which urges for equipping LMMs with multimodal…
Multi-label classification (MLC) studies the problem where each instance is associated with multiple relevant labels, which leads to the exponential growth of output space. MLC encourages a popular framework named label compression (LC) for…
Multilingual sequence-to-sequence models perform poorly with increased language coverage and fail to consistently generate text in the correct target language in few-shot settings. To address these challenges, we propose mmT5, a modular…
Evaluation of machine learning models typically emphasizes final accuracy, overlooking the cost of adaptation: the cumulative errors incurred while learning from scratch. Guess-and- Learn (G&L) v1.0 addresses this gap by measuring…
The multi-label classification problem has generated significant interest in recent years. However, existing approaches do not adequately address two key challenges: (a) the ability to tackle problems with a large number (say millions) of…
Learning modality-fused representations and processing unaligned multimodal sequences are meaningful and challenging in multimodal emotion recognition. Existing approaches use directional pairwise attention or a message hub to fuse…
Learning from multiple modalities, such as audio and video, offers opportunities for leveraging complementary information, enhancing robustness, and improving contextual understanding and performance. However, combining such modalities…
Learning with Noisy Labels (LNL) has attracted significant attention from the research community. Many recent LNL methods rely on the assumption that clean samples tend to have "small loss". However, this assumption always fails to…
The analysis of mixed data has been raising challenges in statistics and machine learning. One of two most prominent challenges is to develop new statistical techniques and methodologies to effectively handle mixed data by making the data…
Class imbalance in supervised classification often degrades model performance by biasing predictions toward the majority class, particularly in critical applications such as medical diagnosis and fraud detection. Traditional oversampling…