SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.05714 · 2024

Enhancing Temporal Modeling of Video LLMs via Time Gating

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
lavi-lab/tg-vid canonical 6 of 9
FunctionStatusWhere it lives
RandomMaskingGenerator Ran lavi-lab/tg-vid/stllm/models/utils.py
pointer only (licence: NONE) · get_code("8bd2d829faa2f7b2")
apply_rotary_pos_emb Ran lavi-lab/tg-vid/stllm/models/modeling_llama_mem.py
pointer only (licence: NONE) · get_code("9b4dff79d5e6102c")
disabled_train Ran lavi-lab/tg-vid/stllm/models/blip2.py
pointer only (licence: NONE) · get_code("4cb732f513d69dfd")
get_sinusoid_encoding_table Ran lavi-lab/tg-vid/stllm/models/utils.py
pointer only (licence: NONE) · get_code("da651e3979a18f84")
rotate_half Ran lavi-lab/tg-vid/stllm/models/modeling_llama_mem.py
pointer only (licence: NONE) · get_code("b99eea6376d1e212")
tile Ran lavi-lab/tg-vid/stllm/models/base_model.py
pointer only (licence: NONE) · get_code("cb33571427334815")
all_gather_with_grad Not yet run lavi-lab/tg-vid/stllm/models/base_model.py
pointer only (licence: NONE) · get_code("0ec9fc2025c16f65")
create_eva_vit_g Not yet run lavi-lab/tg-vid/stllm/models/eva_vit.py
pointer only (licence: NONE) · get_code("ce86d2ef6c0e458f")
forward Not yet run lavi-lab/tg-vid/stllm/models/peft_model.py
pointer only (licence: NONE) · get_code("515cc4dd73dc0caf")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Video Large Language Models (Video LLMs) have achieved impressive performance on video-and-language tasks, such as video question answering. However, most existing Video LLMs neglect temporal information in video data, leading to struggles with temporal-aware video understanding. To address this gap, we propose a Time Gating Video LLM (TG-Vid) designed to enhance temporal modeling through a novel Time Gating module (TG). The TG module employs a time gating mechanism on its sub-modules, comprising gating spatial attention, gating temporal attention, and gating MLP. This architecture enables our model to achieve a robust understanding of temporal information within videos. Extensive evaluation of temporal-sensitive video benchmarks (i.e., MVBench, TempCompass, and NExT-QA) demonstrates that our TG-Vid model significantly outperforms the existing Video LLMs. Further, comprehensive ablation studies validate that the performance gains are attributed to the designs of our TG module. Our code is available at https://github.com/LaVi-Lab/TG-Vid.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.05714")
get_code_for_paper("2410.05714")
have("2410.05714")

Connect an agent — have() is free.