Related papers: Efficient Masked AutoEncoder for Video Object Coun…
Deep learning models have achieved excellent recognition results on large-scale video benchmarks. However, they perform poorly when applied to videos with rare scenes or objects, primarily due to the bias of existing video datasets. We…
Dense video captioning aims to generate text descriptions for all events in an untrimmed video. This involves both detecting and describing events. Therefore, all previous methods on dense video captioning tackle this problem by building…
Recent advances in diffusion models have demonstrated remarkable capabilities in video generation. However, the computational intensity remains a significant challenge for practical applications. While feature caching has been proposed to…
Multi-object tracking (MOT) is a crucial component of situational awareness in military defense applications. With the growing use of unmanned aerial systems (UASs), MOT methods for aerial surveillance is in high demand. Application of MOT…
Tiny object detection plays a vital role in drone surveillance, remote sensing, and autonomous systems, enabling the identification of small targets across vast landscapes. However, existing methods suffer from inefficient feature leverage…
Camouflaged Object Detection (COD) is a challenging task in computer vision due to the high similarity between camouflaged objects and their surroundings. Existing COD methods primarily employ semantic segmentation, which suffers from…
Exploring robust and efficient association methods has always been an important issue in multiple-object tracking (MOT). Although existing tracking methods have achieved impressive performance, congestion and frequent occlusions still pose…
Referring expression counting (REC) algorithms are for more flexible and interactive counting ability across varied fine-grained text expressions. However, the requirement for fine-grained attribute understanding poses challenges for prior…
Self-supervised pre-training for images without labels has recently achieved promising performance in image classification. The success of transformer-based methods, ViT and MAE, draws the community's attention to the design of backbone…
Video understanding has witnessed significant progress with recent video foundation models demonstrating strong performance owing to self-supervised pre-training objectives; Masked Autoencoders (MAE) being the design of choice.…
Learning-based lossless image compression employs pixel-based or subimage-based auto-regression for probability estimation, which achieves desirable performances. However, the existing works only consider context dependencies in one…
The hematology analytics used for detection and classification of small blood components is a significant challenge. In particular, when objects exists as small pixel-sized entities in a large context of similar objects. Deep learning…
Vision Transformers (ViTs) outperforms convolutional neural networks (CNNs) in several vision tasks with its global modeling capabilities. However, ViT lacks the inductive bias inherent to convolution making it require a large amount of…
Autonomous driving systems require a comprehensive understanding of the environment, achieved by extracting visual features essential for perception, planning, and control. However, models trained solely on single-task objectives or generic…
Indiscernible marine object counting encounters numerous challenges, including limited visibility in underwater scenes, mutual occlusion and overlap among objects, and the dynamic similarity in appearance, color, and texture between the…
Masked autoencoders (MAE) have recently succeeded in self-supervised vision representation learning. Previous work mainly applied custom-designed (e.g., random, block-wise) masking or teacher (e.g., CLIP)-guided masking and targets.…
We present Flex, an efficient and effective scene encoder that addresses the computational bottleneck of processing high-volume multi-camera data in end-to-end autonomous driving. Flex employs a small set of learnable scene tokens to…
Understanding the world from multiple perspectives is essential for intelligent systems operating together, where segmenting common objects across different views remains an open problem. We introduce a new approach that re-defines…
Learning 3D representation plays a critical role in masked autoencoder (MAE) based pre-training methods for point cloud, including single-modal and cross-modal based MAE. Specifically, although cross-modal MAE methods learn strong 3D…
This paper presents a novel approach to processing multimodal data for dynamic emotion recognition, named as the Multimodal Masked Autoencoder for Dynamic Emotion Recognition (MultiMAE-DER). The MultiMAE-DER leverages the closely correlated…