BundleNet is a neural network-based mechanism specifically designed for joint advertising in multi-slot settings, achieving state-of-the-art performance.
Explore technology by industry and role
Newest additions first. Explore past and current notes by industry and role.
All notes
Newest additions first. Explore past and current notes by industry and role.
Integrates bid values into retrieval scoring function to ensure economic consistency
A lightweight bidding algorithm combines traffic forecasting with mathematical optimal bidding formulas to achieve efficient real-time decisions.
A multimodal model that automatically summarizes video ads by focusing on commercially valuable content.
Integrates user behaviors across diverse advertising and content domains to build unified commercial behavior trajectories
A new regret minimization model that accounts for interaction between online and offline advertising modes is proposed
Advertising clipping is redefined as a shot selection problem with audio-visual fusion emphasis.
A three-market mechanism—selling, exchange, and buying—is proposed to incentivize merchant data sharing despite customer poaching concerns.
A method to estimate emotions from scene-level expression features without external data
A comprehensive model of the advertising ecosystem is proposed to address privacy leakage issues
A dynamic cooperative advertising optimization model incorporating time-varying quality scores is proposed
Immersive XR advertising increases empathic engagement with virtual products
Integrates text generation and performance alignment within a single end-to-end model via policy learning
Achieves deep integration between generation and ranking stages to resolve objective misalignment.
TikTok's algorithmic targeting of minors in undisclosed promotional content is empirically demonstrated