Related papers: Object-Attribute-Relation Model Driven Adaptive Hi…
Autoregressive (AR) video generative models rely on video tokenizers that compress pixels into discrete token sequences. The length of these token sequences is crucial for balancing reconstruction quality against downstream generation…
The increasing complexity of modern applications demands wireless networks capable of real time adaptability and efficient resource management. The Open Radio Access Network (O-RAN) architecture, with its RAN Intelligent Controller (RIC)…
Reasoning about images/objects and their hierarchical interactions is a key concept for the next generation of computer vision approaches. Here we present a new framework to deal with it through a visual hierarchical context-based…
With the rapid development of multimodal learning, the image-text matching task, as a bridge connecting vision and language, has become increasingly important. Based on existing research, this study proposes an innovative visual semantic…
Ubiquitous image transmission in emerging applications brings huge overheads to limited wireless resources. Since that text has the characteristic of conveying a large amount of information with very little data, the transmission of the…
In existing semantic communication systems for image transmission, some images are generally reconstructed with considerably low quality. As a result, the reliable transmission of each image cannot be guaranteed, bringing significant…
We introduce a novel deep learning-based audio-visual quality (AVQ) prediction model that leverages internal features from state-of-the-art unimodal predictors. Unlike prior approaches that rely on simple fusion strategies, our model…
Unmanned aerial vehicle (UAV) downlink transmission facilitates critical time-sensitive visual applications but is fundamentally constrained by bandwidth scarcity and dynamic channel impairments. The rapid fluctuation of the air-to-ground…
Open-vocabulary Scene Graph Generation (OV-SGG) overcomes the limitations of the closed-set assumption by aligning visual relationship representations with open-vocabulary textual representations. This enables the identification of novel…
Generative semantic communication uses receiver-side generative priors to reconstruct visual content from compact semantics, making it attractive for bandwidth-limited multimedia delivery. For video, reliable recovery remains difficult…
Achieving precise visual localization in GPS-limited urban environments poses significant challenges for resource-constrained mobile platforms, particularly under strict bandwidth, memory, and processing limitations. Inspired by mammalian…
Adaptive video streaming relies on the construction of efficient bitrate ladders to deliver the best possible visual quality to viewers under bandwidth constraints. The traditional method of content dependent bitrate ladder selection…
We propose Context-aware Video-text Alignment (CVA), a novel framework to address a significant challenge in video temporal grounding: achieving temporally sensitive video-text alignment that remains robust to irrelevant background context.…
Emotion recognition in conversations is challenging due to the multi-modal nature of the emotion expression. We propose a hierarchical cross-attention model (HCAM) approach to multi-modal emotion recognition using a combination of recurrent…
Multimodal Large Language Models (MLLMs) show strong performance in Visual Question Answering (VQA) but remain limited in fine-grained reasoning due to low-resolution inputs and noisy attention aggregation. We propose \textbf{Head Aware…
This paper proposes a hierarchical attentional neural translation model which focuses on enhancing source-side hierarchical representations by covering both local and global semantic information using a bidirectional tree-based encoder. To…
Our current technological era is flooded with smart devices that provide significant computational resources that require optimal video communications solutions. Optimal and dynamic management of video bitrate, quality and energy demands…
Recently, pseudo analog transmission has gained increasing attentions due to its ability to alleviate the cliff effect in video multicast scenarios. The existing pseudo analog systems are sorely optimized under the minimum mean squared…
Multi-objective alignment for text-to-image generation is commonly implemented via static linear scalarization, but fixed weights often fail under heterogeneous rewards, leading to optimization imbalance where models overfit high-variance,…
Benefiting from the inductive biases learned from large-scale datasets, open-vocabulary semantic segmentation (OVSS) leverages the power of vision-language models, such as CLIP, to achieve remarkable progress without requiring task-specific…