Search Results for author:
Found 7 papers, 1 papers with code
MonoDETRNext: Next-generation Accurate and Efficient Monocular 3D Object Detection Method
We posit that MonoDETRNext establishes a new benchmark in monocular 3D object detection and opens avenues for future research.
Motion State: A New Benchmark Multiple Object Tracking
Furthermore, to gauge the method's adeptness in discerning object motion states, we introduce the Motion State Validation F1 (MVF1) metric.
DecoderTracker: Decoder-Only Method for Multiple-Object Tracking
Decoder-only models, such as GPT, have demonstrated superior performance in many areas compared to traditional encoder-decoder structure transformer models.
A Creative Industry Image Generation Dataset Based on Captions
Most image generation methods are difficult to precisely control the properties of the generated images, such as structure, scale, shape, etc., which limits its large-scale application in creative industries such as conceptual design and graphic design, and so on.
Towards Micro-video Thumbnail Selection via a Multi-label Visual-semantic Embedding Model
Towards this end, we present a multi-label visual-semantic embedding model to estimate the similarity between the pair of each frame and the popular topics that users are interested in.
A Benchmark Dataset for Micro-video Thumbnail Selection
Towards this end, we construct a large-scale dataset for the micro-video thumbnails.
Hardness Sampling for Self-Training Based Transductive Zero-Shot Learning
Addressing this problem, we first empirically analyze the roles of unseen-class samples with different degrees of hardness in the training process based on the uneven prediction phenomenon found in many ZSL methods, resulting in three observations.
