Yujin Wang

Taehoon Kim, Pyunghwan Ahn, Sangyun Kim et al. · nvidia, utoronto

In this report, we introduce NICE (New frontiers for zero-shot Image Captioning Evaluation) project and share the results and outcomes of 2023 challenge. This project is designed to challenge the computer vision community to develop robust image captioning models that advance the state-of-the-art both in terms of accuracy and fairness. Through the challenge, the image captioning models were tested using a new evaluation dataset that includes a large variety of visual concepts from many domains. There was no specific training data provided for the challenge, and therefore the challenge entries were required to adapt to new types of image descriptions that had not been seen during training. This report includes information on the newly proposed NICE dataset, evaluation methods, challenge results, and technical details of top-ranking entries. We expect that the outcomes of the challenge will contribute to the improvement of AI models on various vision-language tasks.

Ziran Zhang, Xiaohui Li, Yihao Liu et al.

Video frame interpolation (VFI) in scenarios with large motion remains challenging due to motion ambiguity between frames. While event cameras can capture high temporal resolution motion information, existing event-based VFI methods struggle with limited training data and complex motion patterns. In this paper, we introduce Event-Guided Video Diffusion Model (EGVD), a novel framework that leverages the powerful priors of pre-trained stable video diffusion models alongside the precise temporal information from event cameras. Our approach features a Multi-modal Motion Condition Generator (MMCG) that effectively integrates RGB frames and event signals to guide the diffusion process, producing physically realistic intermediate frames. We employ a selective fine-tuning strategy that preserves spatial modeling capabilities while efficiently incorporating event-guided temporal information. We incorporate input-output normalization techniques inspired by recent advances in diffusion modeling to enhance training stability across varying noise levels. To improve generalization, we construct a comprehensive dataset combining both real and simulated event data across diverse scenarios. Extensive experiments on both real and simulated datasets demonstrate that EGVD significantly outperforms existing methods in handling large motion and challenging lighting conditions, achieving substantial improvements in perceptual quality metrics (27.4% better LPIPS on Prophesee and 24.1% on BSRGB) while maintaining competitive fidelity measures. Code and datasets available at: https://github.com/OpenImagingLab/EGVD.

Gangwei Xu, Yujin Wang, Jinwei Gu et al.

Reconstructing High Dynamic Range (HDR) video from image sequences captured with alternating exposures is challenging, especially in the presence of large camera or object motion. Existing methods typically align low dynamic range sequences using optical flow or attention mechanism for deghosting. However, they often struggle to handle large complex motions and are computationally expensive. To address these challenges, we propose a robust and efficient flow estimator tailored for real-time HDR video reconstruction, named HDRFlow. HDRFlow has three novel designs: an HDR-domain alignment loss (HALoss), an efficient flow network with a multi-size large kernel (MLK), and a new HDR flow training scheme. The HALoss supervises our flow network to learn an HDR-oriented flow for accurate alignment in saturated and dark regions. The MLK can effectively model large motions at a negligible cost. In addition, we incorporate synthetic data, Sintel, into our training dataset, utilizing both its provided forward flow and backward flow generated by us to supervise our flow network, enhancing our performance in large motion regions. Extensive experiments demonstrate that our HDRFlow outperforms previous methods on standard benchmarks. To the best of our knowledge, HDRFlow is the first real-time HDR video reconstruction method for video sequences captured with alternating exposures, capable of processing 720p resolution inputs at 25ms.

Yujin Wang, Tianyi Wang, Quanfeng Liu et al.

Accurate short-horizon trajectory prediction is pivotal for safe and reliable autonomous driving, yet existing vision-language models (VLMs) often fail to effectively ground their reasoning in scene dynamics and domain knowledge. To address this challenge, this paper introduces KEPT, a knowledge-enhanced VLM framework that predicts ego trajectories directly from consecutive front-view driving frames. KEPT couples a temporal frequency-spatial fusion (TFSF) video encoder, trained via self-supervised learning with hard-negative mining, with a scalable k-means + HNSW retrieval stack that supplies scene-aligned exemplars. Retrieved priors are embedded into chain-of-thought (CoT) prompts with explicit planning constraints, while a triple-stage fine-tuning schedule incrementally aligns the language head to metric spatial cues, physically feasible motion, and temporally conditioned front-view planning. Evaluated on nuScenes dataset, KEPT achieves state-of-the-art performance across open-loop protocols: under NoAvg, it achieves 0.70m average L2 with a 0.21\% collision rate; under TemAvg with lightweight ego status, it attains 0.31m average L2 and a 0.07\% collision rate. Ablation studies show that all three fine-tuning stages contribute complementary benefits, and that using Top-2 retrieved exemplars yields the best accuracy-safety trade-off. The k-means-clustered HNSW index delivers sub-millisecond retrieval latency, supporting practical deployment. These results indicate that retrieval-augmented, CoT-guided VLMs offer a promising, data-efficient pathway toward interpretable and trustworthy autonomous driving.

Xin Xia, Yujin Wang, Jun Zhou et al.

Patent analysis highly relies on concise and interpretable document representations, referred to as patent portraits. Keyphrases, both present and absent, are ideal candidates for patent portraits due to their brevity, representativeness, and clarity. In this paper, we introduce KAPPA, an integrated framework designed to construct keyphrase-based patent portraits and enhance patent analysis. KAPPA operates in two phases: patent portrait construction and portrait-based analysis. To ensure effective portrait construction, we propose a semantic-calibrated keyphrase generation paradigm that integrates pre-trained language models with a prompt-based hierarchical decoding strategy to leverage the multi-level structural characteristics of patents. For portrait-based analysis, we develop a comprehensive framework that employs keyphrase-based patent portraits to enable efficient and accurate patent analysis. Extensive experiments on benchmark datasets of keyphrase generation, the proposed model achieves significant improvements compared to state-of-the-art baselines. Further experiments conducted on real-world patent applications demonstrate that our keyphrase-based portraits effectively capture domain-specific knowledge and enrich semantic representation for patent analysis tasks.