Related papers: Task-Oriented Feature Compression for Multimodal U…
Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hierarchical features, leading to information loss in…
Long video understanding is inherently challenging for vision-language models (VLMs) because of the extensive number of frames. With each video frame typically expanding into tens or hundreds of tokens, the limited context length of large…
With the increasing number and enhanced capabilities of IoT devices in smart buildings, these devices are evolving beyond basic data collection and control to actively participate in deep learning tasks. Federated Learning (FL), as a…
Large Vision-Language Models (LVLMs) excel in visual understanding and reasoning, but the excessive visual tokens lead to high inference costs. Although recent token reduction methods mitigate this issue, they mainly target single-turn…
Co-clustering targets on grouping the samples (e.g., documents, users) and the features (e.g., words, ratings) simultaneously. It employs the dual relation and the bilateral information between the samples and features. In many realworld…
Video-language models (VLMs) face rapid inference costs as visual token counts scale with video length. For example, 32 frames at $448{\times}448$ resolution already yield >8,000 visual tokens in Qwen3-VL, making LLM prefill the dominant…
Slow inference speed is one of the most crucial concerns for deploying multi-view 3D detectors to tasks with high real-time requirements like autonomous driving. Although many sparse query-based methods have already attempted to improve the…
Camouflaged object detection (COD) is a challenging task due to the low boundary contrast between the object and its surroundings. In addition, the appearance of camouflaged objects varies significantly, e.g., object size and shape,…
For multimodal tasks, a good feature extraction network should extract information as much as possible and ensure that the extracted feature embedding and other modal feature embedding have an excellent mutual understanding. The latter is…
The area of Video Camouflaged Object Detection (VCOD) presents unique challenges in the field of computer vision due to texture similarities between target objects and their surroundings, as well as irregular motion patterns caused by both…
In wireless Internet of things (IoT), the sensors usually have limited bandwidth and power resources. Therefore, in a distributed setup, each sensor should compress and quantize the sensed observations before transmitting them to a fusion…
Multimodal semantic communication has great potential to enhance downstream task performance by integrating complementary information across modalities. This paper introduces ProMSC-MIS, a novel Prompt-based Multimodal Semantic…
Reducing communication overhead in federated learning (FL) is challenging but crucial for large-scale distributed privacy-preserving machine learning. While methods utilizing sparsification or others can largely lower the communication…
Federated inference enhances LLM performance in edge computing through weighted averaging of distributed model predictions. However, autoregressive LLM inference requires frequent full-model forward passes across workers, severely limiting…
Late fusion multi-view clustering (LFMVC) has become a rapidly growing class of methods in the multi-view clustering (MVC) field, owing to its excellent computational speed and clustering performance. One bottleneck faced by existing late…
The emergence of multimodal foundation models has revolutionized learning paradigms by enabling joint understanding across diverse data types. In the context of next-generation wireless networks, integrating sensing and communication…
Infrared-visible image fusion methods aim at generating fused images with good visual quality and also facilitate the performance of high-level tasks. Indeed, existing semantic-driven methods have considered semantic information injection…
Multimodal representation learning produces high-dimensional embeddings that align diverse modalities in a shared latent space. While this enables strong generalization, it also introduces scalability challenges, both in terms of storage…
Over the last decade, deep learning has shown great success at performing computer vision tasks, including classification, super-resolution, and style transfer. Now, we apply it to data compression to help build the next generation of…
Optimizing task-to-core allocation can substantially reduce power consumption in multi-core platforms without degrading user experience. However, existing approaches overlook critical factors such as parallelism, compute intensity, and…